[1]
Liu, X., Lei, H., Liu, Y., Liu, Y. and Hu, W. 2026. ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 1 (Mar. 2026), 773-781. DOI:https://doi.org/10.1609/aaai.v40i1.37044.