© 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. 71574
    Prev
    Next
    INDEX
    Explanations

    filter

    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
    Negative Logits
    -server
    -0.07
     ਯ
    -0.07
     fak
    -0.07
     बुद्ध
    -0.07
     ਦਰ
    -0.07
    numbers
    -0.07
     eum
    -0.07
    雄
    -0.07
    /app
    -0.07
     वाली
    -0.07
    POSITIVE LOGITS
    خانه
    0.09
     дизайн
    0.09
     applied
    0.09
    0.08
     coma
    0.08
    广播
    0.08
     keçiril
    0.08
     المض
    0.08
     broadcast
    0.08
    াউ
    0.08
    Activations Density 0.003%
    No Known Activations