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

    Neuronpedia

    APICircuit 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. 58584
    Prev
    Next
    INDEX
    Explanations

    pro

    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
    FE
    -0.08
     violation
    -0.08
     composer
    -0.07
     شعر
    -0.07
     violations
    -0.07
     страхов
    -0.07
     spreadsheet
    -0.07
    nasium
    -0.07
     subsidy
    -0.07
    ாம்
    -0.07
    POSITIVE LOGITS
    -inflammatory
    0.09
     impetus
    0.08
     swirling
    0.08
     Cycl
    0.08
     appetite
    0.08
     Ziele
    0.08
     inflammatory
    0.08
    Cycl
    0.08
    ائدة
    0.07
     cycl
    0.07
    Activations Density 0.001%

    No Known Activations