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. 112099
    Prev
    Next
    INDEX
    Explanations

    Horizontal or vertical

    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
     Zurich
    -0.07
     bury
    -0.07
    place
    -0.07
     constamment
    -0.07
     свої
    -0.07
    olim
    -0.07
    öm
    -0.07
    bury
    -0.07
    ારીઓ
    -0.07
     FIFA
    -0.07
    POSITIVE LOGITS
     halaman
    0.10
    Man
    0.09
     эле
    0.08
     pej
    0.08
     страницу
    0.08
     Man
    0.08
    第一页
    0.08
    ด้าน
    0.08
     perjalanan
    0.08
     صفحه
    0.08
    Activations Density 0.008%

    No Known Activations