© 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. 7-RESID-POST-AA
    11. 1269
    Prev
    Next
    INDEX
    Explanations

    lev

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Climate
    -0.09
     climate
    -0.09
    (scope
    -0.09
     آواز
    -0.08
    Climate
    -0.08
     голос
    -0.08
    áž
    -0.08
     voz
    -0.08
    voice
    -0.08
     savour
    -0.08
    POSITIVE LOGITS
     steal
    0.08
     annul
    0.07
     Cot
    0.07
    'd
    0.07
     sulfate
    0.07
     Endless
    0.07
     Iv
    0.07
    'et
    0.07
     condenser
    0.07
     '+
    0.07
    Activations Density 0.000%

    No Known Activations