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. 58709
    Prev
    Next
    INDEX
    Explanations

    mixed languages and/or programming

    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
     scalable
    -0.09
    clean
    -0.08
     CLEAN
    -0.08
     Kart
    -0.08
    ่าส
    -0.08
     FOR
    -0.08
    foreach
    -0.07
    ерг
    -0.07
    扫
    -0.07
    -0.07
    POSITIVE LOGITS
     घटन
    0.08
     dogod
    0.07
     নাট
    0.07
     қыс
    0.07
     qay
    0.07
    �
    0.07
     culpa
    0.07
    嫁
    0.07
     कुन
    0.07
     bir
    0.07
    Activations Density 0.000%

    No Known Activations