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. 30557
    Prev
    Next
    INDEX
    Explanations

    is

    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
     благодаря
    -0.08
    =A
    -0.07
    UP
    -0.07
    _SUCCESS
    -0.07
     mellow
    -0.07
     inoxidable
    -0.07
     вку
    -0.07
     seeker
    -0.07
     започ
    -0.07
    _success
    -0.07
    POSITIVE LOGITS
     الأطفال
    0.12
    儿童
    0.12
     শিশু
    0.12
     gyermek
    0.12
    เด็ก
    0.11
     ಮಕ್ಕಳ
    0.11
     crianças
    0.11
     juvenile
    0.11
     للأطفال
    0.11
     കുട്ട
    0.11
    Activations Density 0.024%

    No Known Activations