© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44661
    Prev
    Next
    INDEX
    Explanations

    percentage increase/decrease

    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
    -supported
    -0.08
     vap
    -0.08
    Evidence
    -0.08
    vidence
    -0.07
    Supported
    -0.07
    Realm
    -0.07
     retired
    -0.07
     trio
    -0.07
    icions
    -0.07
     보
    -0.07
    POSITIVE LOGITS
     mengalami
    0.09
     nouve
    0.09
    loch
    0.09
     Herkunft
    0.09
     sanhi
    0.08
    തമ
    0.08
     numerator
    0.08
    leriniň
    0.08
    umbuhan
    0.08
     difference
    0.08
    Activations Density 0.025%

    No Known Activations