1.5k citations · 1.5k across the 6 of their papers we have counts for
6 papers
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
Persona Features Control Emergent Misalignment
Miles Wang, Tom Dupré la Tour, Olivia Watkins +8
Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that…
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
Aleksandar Makelov, George Lange, Neel Nanda
Disentangling model activations into meaningful features is a central problem in interpretability. However, the absence of ground-truth for these features in realistic scenarios ma…
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching
Aleksandar Makelov, Georg Lange, Neel Nanda
Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activat…
Rethinking Backdoor Attacks
Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov +4
In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against s…
Towards Deep Learning Models Resistant to Adversarial Attacks
Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt +2
Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorr…