© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70270
    Prev
    Next
    INDEX
    Explanations

    table of contents/page numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     gelden
    -0.08
    Nutrition
    -0.08
     APO
    -0.08
     intenz
    -0.07
     meilleurs
    -0.07
    imers
    -0.07
     costru
    -0.07
    -0.07
    鼓
    -0.07
    @Many
    -0.07
    POSITIVE LOGITS
     страниц
    0.11
     Pages
    0.10
     pages
    0.10
    หน้า
    0.10
     페이지
    0.10
     páginas
    0.10
     locating
    0.09
    Pages
    0.09
    ページ
    0.09
     Chapter
    0.09
    Activations Density 0.007%
    No Known Activations