© 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. 71551
    Prev
    Next
    INDEX
    Explanations

    to

    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
    (w
    -0.07
     veh
    -0.07
     cca
    -0.07
    Veh
    -0.07
     Hef
    -0.07
    τερο
    -0.07
    еров
    -0.07
     composition
    -0.07
     navy
    -0.07
    hmen
    -0.07
    POSITIVE LOGITS
     النجاح
    0.09
     सफलता
    0.09
     Brown
    0.08
     brown
    0.08
     enlightenment
    0.08
    сяг
    0.08
    满意
    0.08
     മികച്ച
    0.08
    justice
    0.08
     만족
    0.08
    Activations Density 0.037%

    No Known Activations