© 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. 71197
    Prev
    Next
    INDEX
    Explanations

    Shawshank Redemption

    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
     শিশ
    -0.08
    asc
    -0.08
    iedo
    -0.08
     Ethical
    -0.08
     ziyaret
    -0.08
    edu
    -0.08
    visited
    -0.07
    gress
    -0.07
     Basilica
    -0.07
    nier
    -0.07
    POSITIVE LOGITS
    高速
    0.09
     music
    0.08
     علیه
    0.08
     علیہ
    0.08
     అధ
    0.07
    ２０１
    0.07
     जय
    0.07
     विजय
    0.07
    _HIGH
    0.07
     ஆரம்ப
    0.07
    Activations Density 0.001%

    No Known Activations