LIU, X.; LEI, H.; LIU, Y.; LIU, Y.; HU, W. ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 1, p. 773-781, 2026. DOI: 10.1609/aaai.v40i1.37044. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37044. Acesso em: 29 apr. 2026.