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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19733
    Prev
    Next
    INDEX
    Explanations

    problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Вот
    -0.08
     adorned
    -0.08
     fiction
    -0.08
     poesía
    -0.08
    完整版
    -0.08
     Чтобы
    -0.08
     thirty
    -0.08
     услыш
    -0.07
    fiction
    -0.07
     poésie
    -0.07
    POSITIVE LOGITS
     مشاكل
    0.13
     المشكلة
    0.13
     проблемы
    0.13
     проблема
    0.12
     সমস্যা
    0.12
     مشكلة
    0.12
     కారణ
    0.12
     problèmes
    0.12
     সমস্য
    0.11
     مشکلات
    0.11
    Activations Density 0.040%

    No Known Activations