docs: update README news

Author: dest1n1s

README.md

@@ -7,17 +7,19 @@
 
 ## News
 
-- 2025.9.23 We leverage **Crosscoder** to track feature evolution across pre-training snapshots. Link: [Evolution of Concepts in Language Model Pre-Training](https://www.arxiv.org/abs/2509.17196).
+- 2026.2.12 We introduce **Complete Replacement Models (CRMs)**, which combine transcoders and Lorsas to fully sparsify language models. Link: [Bridging the Attention Gap: Complete Replacement Models for Complete Circuit Tracing](https://interp.open-moss.com/posts/complete-replacement).
+
+- 2025.9.23 We leverage **Crosscoder** to track feature evolution across pre-training snapshots. Link: [Evolution of Concepts in Language Model Pre-Training](https://www.arxiv.org/abs/2509.17196) (ICLR 2026).
 
 - 2025.8.23 We identify a prevalent low-rank structure in attention outputs as the key cause of dead features, and propose **Active Subspace Initialization** to improve sparse dictionary learning on these low-rank activations. Link: [Attention Layers Add Into Low-Dimensional Residual Subspaces](https://arxiv.org/abs/2508.16929).
 
-- 2025.4.29 We introduce **Low-Rank Sparse Attention (Lorsa)** to attack attention superposition, extracting tens of thousands of true attention units from LLM attention layers. Link: [Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition](https://arxiv.org/abs/2504.20938).
+- 2025.4.29 We introduce **Low-Rank Sparse Attention (Lorsa)** to attack attention superposition, extracting tens of thousands of true attention units from LLM attention layers. Link: [Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition](https://arxiv.org/abs/2504.20938) (ICLR 2026).
 
 - 2024.10.29 We introduce **Llama Scope**, our first contribution to the open-source Sparse Autoencoder ecosystem. Stay tuned! Link: [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](http://arxiv.org/abs/2410.20526).
 
-- 2024.10.9 Transformers and Mambas are mechanistically similar in both feature and circuit level. Can we follow this line and find **universal motifs and fundamental differences between language model architectures**? Link: [Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures](https://arxiv.org/pdf/2410.06672).
+- 2024.10.9 Transformers and Mambas are mechanistically similar in both feature and circuit level. Can we follow this line and find **universal motifs and fundamental differences between language model architectures**? Link: [Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures](https://arxiv.org/pdf/2410.06672) (ICLR 2025).
 
-- 2024.5.22 We propose hierarchical tracing, a promising method to **scale up sparse feature circuit analysis** to industrial size language models! Link: [Automatically Identifying Local and Global Circuits with Linear Computation Graphs](https://arxiv.org/pdf/2405.13868).
+- 2024.5.22 We propose hierarchical tracing, a promising method to **scale up sparse feature circuit analysis** to industrial sized language models! Link: [Automatically Identifying Local and Global Circuits with Linear Computation Graphs](https://arxiv.org/pdf/2405.13868) (ICML 2024 MI Workshop).
 
 - 2024.2.19 Our first attempt on SAE-based circuit analysis for Othello-GPT leads us to **an example of Attention Superposition in the wild**! Link: [Dictionary learning improves patch-free circuit discovery in mechanistic interpretability: A case study on othello-gpt](https://arxiv.org/pdf/2402.12201).