Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse autoencoder framework that overcomes this by enforcing one-to-one concept-neuron mappings. By systematically labeling concepts during training, our method achieves feature centralization, binding each concept to a single, interpretable neuron. This enables highly targeted and efficient concept erasure. SAEmnesia reduces hyperparameter search by 96.7% and achieves a 9.2% improvement over the state-of-the-art on the UnlearnCanvas benchmark. Our method also demonstrates superior scalability in sequential unlearning, improving accuracy by 28.4% when removing nine objects, establishing a new standard for precise and controllable concept erasure. Moreover, SAEmnesia mitigates the possibility of generating unwanted content under adversarial attack and effectively removes nudity when evaluated with I2P.
@article{arxiv.2509.21379,
title = {SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders},
author = {Enrico Cassano and Riccardo Renzulli and Marco Nurisso and Mirko Zaffaroni and Alan Perotti and Marco Grangetto},
journal= {arXiv preprint arXiv:2509.21379},
year = {2025}
}