© 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. 68084
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    akte
    -0.08
     behar
    -0.07
     bespoke
    -0.07
     hack
    -0.07
    formin
    -0.07
    hack
    -0.07
    ori
    -0.07
     Autob
    -0.07
     démarche
    -0.07
     الأش
    -0.07
    POSITIVE LOGITS
    0.07
     marg
    0.07
     evaluated
    0.07
     mantener
    0.07
     воп
    0.07
     Zum
    0.07
     Runde
    0.07
     соглаш
    0.07
    Kommentar
    0.07
     വിഷ
    0.07
    Activations Density 0.046%
    No Known Activations