© 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. 109961
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     ocasião
    -0.08
    DAT
    -0.08
    restaurants
    -0.08
    REB
    -0.08
    ОН
    -0.08
    iously
    -0.08
    øn
    -0.07
     exceptional
    -0.07
     apreci
    -0.07
    iav
    -0.07
    POSITIVE LOGITS
     Presentation
    0.08
     су
    0.08
     заг
    0.08
     стан
    0.08
     Anonymous
    0.07
     danh
    0.07
     Nor
    0.07
    (Rem
    0.07
     pupp
    0.07
     narrator
    0.07
    Activations Density 0.001%

    No Known Activations