© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71483
    Prev
    Next
    INDEX
    Explanations

    code, errors

    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
     deta
    -0.08
     perfectamente
    -0.08
    larımız
    -0.08
     chid
    -0.08
     parfaitement
    -0.08
     attrakt
    -0.08
     Launcher
    -0.07
    authenticated
    -0.07
     atrak
    -0.07
     attractive
    -0.07
    POSITIVE LOGITS
    关键词
    0.11
     keywords
    0.10
    \b
    0.09
    Keywords
    0.09
    .keyword
    0.09
    keywords
    0.09
     unmistak
    0.09
    _keywords
    0.09
     explicitly
    0.09
    indic
    0.08
    Activations Density 0.032%

    No Known Activations