© 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. 23-RESID-POST-AA
    11. 52078
    Prev
    Next
    INDEX
    Explanations

    ém/com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     representatives
    -0.08
    (df
    -0.08
    .www
    -0.07
     nominees
    -0.07
     scholars
    -0.07
    ком
    -0.07
     kit
    -0.07
     представителей
    -0.07
    oidal
    -0.07
    ವೆ
    -0.07
    POSITIVE LOGITS
    arrer
    0.14
    arrage
    0.14
    enc
    0.12
    encer
    0.12
    ença
    0.12
    ences
    0.11
    encé
    0.11
    ENC
    0.11
    ence
    0.11
    enciar
    0.11
    Activations Density 0.000%

    No Known Activations