© 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. 109964
    Prev
    Next
    INDEX
    Explanations

    English language

    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
    本科
    -0.08
     ұсы
    -0.08
     ops
    -0.07
     frozen
    -0.07
     colleagues
    -0.07
     podium
    -0.07
    celer
    -0.07
     colega
    -0.07
     الأرب
    -0.07
     ladies
    -0.07
    POSITIVE LOGITS
    Sum
    0.09
     thay
    0.09
     Sum
    0.08
     Rien
    0.08
     sums
    0.07
    ហ
    0.07
    .eas
    0.07
     handheld
    0.07
     Citrus
    0.07
    bij
    0.07
    Activations Density 0.015%

    No Known Activations