© 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. 109924
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     unfavorable
    -0.07
    -og
    -0.07
     фин
    -0.07
    闻
    -0.07
    赖
    -0.07
    -pound
    -0.07
     Beno
    -0.07
     extensión
    -0.07
    ople
    -0.07
     favorable
    -0.07
    POSITIVE LOGITS
     그리고
    0.07
     ausgesch
    0.07
    option
    0.07
    render
    0.07
    radi
    0.07
    बे
    0.07
     mede
    0.07
    filtered
    0.07
     langkah
    0.07
    दी
    0.07
    Activations Density 0.098%

    No Known Activations