Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90271
    Prev
    Next
    INDEX
    Explanations

    Error

    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
    Touches
    -0.09
    touch
    -0.08
    Italic
    -0.08
    stroke
    -0.07
    场
    -0.07
    vap
    -0.07
    (ed
    -0.07
     touches
    -0.07
    aq
    -0.07
    成
    -0.07
    POSITIVE LOGITS
     sounding
    0.09
     راه
    0.08
     County
    0.08
     نمی
    0.08
     Relief
    0.08
    -paid
    0.08
     payé
    0.08
     zählen
    0.08
     Wirtschafts
    0.08
     کنم
    0.07
    Activations Density 0.000%

    No Known Activations