Chrysos, G. 2026. Beyond Neuron-Level Sparsity: Achieving Faithful and Interpretable LLMs with Mixture of Decoders. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 47 (Mar. 2026), 39811–39812. DOI:https://doi.org/10.1609/aaai.v40i47.41340.