© 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. 109894
    Prev
    Next
    INDEX
    Explanations

    adjust

    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
     disturbance
    -0.08
    区
    -0.08
     langfrist
    -0.08
    597
    -0.08
     tientallen
    -0.07
     carried
    -0.07
    _pic
    -0.07
    ત્ર
    -0.07
    605
    -0.07
     Theodore
    -0.07
    POSITIVE LOGITS
     ра
    0.08
    -controlled
    0.08
     PRES
    0.07
     recall
    0.07
    angkat
    0.07
    Lou
    0.07
     дош
    0.07
     sneak
    0.07
     pam
    0.07
    Rise
    0.07
    Activations Density 0.005%

    No Known Activations