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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63051
    Prev
    Next
    INDEX
    Explanations

    one/a

    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
    achi
    -0.08
    不了了
    -0.08
     масш
    -0.08
    大胆
    -0.07
    ters
    -0.07
     HL
    -0.07
    予
    -0.07
     ஏற்ப
    -0.07
    heits
    -0.07
    尤
    -0.07
    POSITIVE LOGITS
    Except
    0.09
     handful
    0.09
     Except
    0.08
    Ping
    0.08
     shred
    0.08
    pile
    0.08
     siglos
    0.07
    gym
    0.07
     ounce
    0.07
    Remaining
    0.07
    Activations Density 0.013%

    No Known Activations