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. 60909
    Prev
    Next
    INDEX
    Explanations

    economy

    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
     компонентов
    -0.08
     ਤੁ
    -0.08
     vaardigheden
    -0.08
     реализации
    -0.08
    _ACT
    -0.08
     компон
    -0.08
     Skills
    -0.08
     attained
    -0.07
     competencies
    -0.07
     actu
    -0.07
    POSITIVE LOGITS
     agress
    0.08
     ауыр
    0.08
     supr
    0.08
    growth
    0.08
     terá
    0.07
     mõ
    0.07
    anas
    0.07
     suure
    0.07
     Billie
    0.07
    מונה
    0.07
    Activations Density 0.016%

    No Known Activations