© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99273
    Prev
    Next
    INDEX
    Explanations

    pon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verzoek
    -0.08
    hma
    -0.08
     दर्ज
    -0.08
    elijkheid
    -0.08
    erst
    -0.07
     നൽക
    -0.07
     historique
    -0.07
    ighthouse
    -0.07
     Ego
    -0.07
     histórico
    -0.07
    POSITIVE LOGITS
     системе
    0.09
     система
    0.09
     системой
    0.09
     ವ್ಯವಸ್ಥ
    0.09
     системы
    0.08
     nutrient
    0.08
     систему
    0.08
    .Program
    0.07
     ode
    0.07
     werken
    0.07
    Activations Density 0.001%

    No Known Activations