© 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. 19-RESID-POST-AA
    11. 102837
    Prev
    Next
    INDEX
    Explanations

    say π

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .symmetric
    -0.09
     broader
    -0.09
     неп
    -0.08
    非
    -0.08
    داول
    -0.08
     rischio
    -0.08
    guez
    -0.08
     ике
    -0.08
     गैर
    -0.08
     Mercado
    -0.08
    POSITIVE LOGITS
     pinnacle
    0.15
     maximizing
    0.15
     maximize
    0.14
     최고
    0.14
     maxima
    0.14
     pinakam
    0.13
     highest
    0.13
     최고의
    0.13
    highest
    0.13
     Highest
    0.13
    Activations Density 0.011%

    No Known Activations