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. 11-RESID-POST-AA
    6. 42060
    Prev
    Next
    INDEX
    Explanations

    hydration tips

    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
     stability
    -0.08
     instability
    -0.07
     coalition
    -0.07
     রাজনৈতিক
    -0.07
    Won
    -0.07
    攻
    -0.07
     existen
    -0.07
     hars
    -0.07
     Insolvenz
    -0.07
     राजनीतिक
    -0.07
    POSITIVE LOGITS
     hábito
    0.12
     caffeine
    0.12
     الماء
    0.10
     fountains
    0.10
     सेवन
    0.10
     agua
    0.10
     calorie
    0.10
     refill
    0.10
     Habit
    0.10
     uống
    0.10
    Activations Density 0.014%

    No Known Activations