© 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. 71498
    Prev
    Next
    INDEX
    Explanations

    solid

    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
     sử
    -0.08
     nach
    -0.08
    覽
    -0.08
    464
    -0.07
     použ
    -0.07
     زی
    -0.07
    한다
    -0.07
    .naming
    -0.07
    463
    -0.07
    ોચ
    -0.07
    POSITIVE LOGITS
    endet
    0.08
     versed
    0.08
     réputation
    0.08
     enough
    0.07
    基础
    0.07
    -bo
    0.07
    -looking
    0.07
    لبة
    0.07
     shoulder
    0.07
    ైన
    0.07
    Activations Density 0.010%

    No Known Activations