© 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. 71715
    Prev
    Next
    INDEX
    Explanations

    up

    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
     Outline
    -0.09
     Logistic
    -0.08
    .Criteria
    -0.08
    iberal
    -0.08
    ீழ
    -0.08
    .Multi
    -0.08
     Procedures
    -0.08
     Bishop
    -0.07
     Alan
    -0.07
     Convenience
    -0.07
    POSITIVE LOGITS
     lol
    0.09
     slap
    0.09
     depressing
    0.09
     trang
    0.08
     lernen
    0.08
     wła
    0.07
     ээ
    0.07
     synonyms
    0.07
    AAAAAAAA
    0.07
     myth
    0.07
    Activations Density 0.018%

    No Known Activations