Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43814
    Prev
    Next
    INDEX
    Explanations

    LaTeX

    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
    .offer
    -0.09
    (dto
    -0.09
    .Uint
    -0.09
    (validation
    -0.09
     interviewed
    -0.08
    虎
    -0.08
    (xhr
    -0.08
     principios
    -0.08
    (fetch
    -0.08
     Tyson
    -0.08
    POSITIVE LOGITS
    .tex
    0.13
    latex
    0.13
     latex
    0.13
     La
    0.12
     Latex
    0.12
     Debian
    0.11
     bibliography
    0.10
     tik
    0.09
    La
    0.09
     compile
    0.09
    Activations Density 0.011%

    No Known Activations