© 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. 70523
    Prev
    Next
    INDEX
    Explanations

    of

    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
    rep
    -0.09
    acent
    -0.08
    être
    -0.08
    rett
    -0.08
    unehmen
    -0.08
     improb
    -0.08
    atau
    -0.07
     determin
    -0.07
    komb
    -0.07
    (stat
    -0.07
    POSITIVE LOGITS
     peru
    0.08
     ove
    0.08
     మేర
    0.08
     Hawai
    0.08
     neigh
    0.08
     আও
    0.08
     Avalon
    0.08
     ores
    0.07
     Wix
    0.07
    ’affaires
    0.07
    Activations Density 0.053%

    No Known Activations