1.
Liu X, Lei H, Liu Y, Liu Y, Hu W. ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders. AAAI [Internet]. 2026Mar.14 [cited 2026May4];40(1):773-81. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/37044