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. 77268
    Prev
    Next
    INDEX
    Explanations

    2

    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
     ಗ್ರಾಮ
    -0.08
     ഗ്രാമ
    -0.08
    -provider
    -0.08
     generaciones
    -0.08
    五月
    -0.08
     handheld
    -0.07
    -community
    -0.07
    бират
    -0.07
     prag
    -0.07
     గ్రామ
    -0.07
    POSITIVE LOGITS
     पत्र
    0.08
     વ્યક્ત
    0.08
     اړتیا
    0.08
     şəx
    0.08
     sheets
    0.08
     immortal
    0.07
     Gucci
    0.07
     LAST
    0.07
     ponder
    0.07
     vegan
    0.07
    Activations Density 0.004%

    No Known Activations