© 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. 110696
    Prev
    Next
    INDEX
    Explanations

    Multiple languages and currencies

    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
     bisschen
    -0.08
    -0.08
    /non
    -0.07
     abol
    -0.07
    tails
    -0.07
    irib
    -0.07
    ：(
    -0.07
    ща
    -0.07
    <tbody
    -0.07
    터
    -0.07
    POSITIVE LOGITS
     fé
    0.08
    120
    0.08
    132
    0.08
     Angel
    0.08
    110
    0.08
    101
    0.08
     ebenfalls
    0.08
    112
    0.08
     Rudolph
    0.07
     Elo
    0.07
    Activations Density 0.042%
    No Known Activations