© 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. 29529
    Prev
    Next
    INDEX
    Explanations

    Image generation instructions

    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
     diskut
    -0.08
    ंज
    -0.08
    ਕੇ
    -0.08
    ੰਜ
    -0.07
    қын
    -0.07
     ك
    -0.07
     Robbins
    -0.07
    ғыш
    -0.07
     sar
    -0.07
    (Resources
    -0.07
    POSITIVE LOGITS
     соблюдать
    0.09
    brev
    0.08
     malformed
    0.08
     mandatory
    0.08
     соблю
    0.07
    -AA
    0.07
     compliance
    0.07
     Accordingly
    0.07
     mandated
    0.07
     drip
    0.07
    Activations Density 0.010%

    No Known Activations