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. 12767
    Prev
    Next
    INDEX
    Explanations

    calculating area

    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
    એ
    -0.07
     запуска
    -0.07
     nurture
    -0.07
     detrás
    -0.07
     başlad
    -0.07
     upbringing
    -0.07
     contrap
    -0.07
     прап
    -0.07
    中国特色社会主义
    -0.07
     çıkt
    -0.07
    POSITIVE LOGITS
    肉
    0.08
    DECLARE
    0.08
     آن
    0.08
     grosses
    0.07
     المزيد
    0.07
    IMM
    0.07
     Fourn
    0.07
    ILON
    0.07
     غذا
    0.07
     طول
    0.07
    Activations Density 0.012%

    No Known Activations