© 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. 71625
    Prev
    Next
    INDEX
    Explanations

    skip

    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
    (bucket
    -0.09
     bucket
    -0.09
    (Menu
    -0.08
    <Menu
    -0.08
    bucket
    -0.08
    ucket
    -0.08
     plateforme
    -0.08
    	Menu
    -0.08
    Bucket
    -0.07
     couleur
    -0.07
    POSITIVE LOGITS
     annoyed
    0.08
    _SKIP
    0.08
    chon
    0.08
     bỏ
    0.08
     выключ
    0.08
     мень
    0.08
    ancellable
    0.07
    Freedom
    0.07
     blockers
    0.07
     seçim
    0.07
    Activations Density 0.007%

    No Known Activations