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. 113923
    Prev
    Next
    INDEX
    Explanations

    essential oils

    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
     settling
    -0.08
     spur
    -0.07
    áll
    -0.07
     imposed
    -0.07
    וכ
    -0.07
     mid
    -0.07
    ਵਾ
    -0.07
    -copy
    -0.07
    64
    -0.07
     vár
    -0.07
    POSITIVE LOGITS
     Compose
    0.11
    compose
    0.10
     compose
    0.10
     ترکی
    0.09
    Compose
    0.09
    خانه
    0.09
     Sym
    0.09
     oregano
    0.09
     herbs
    0.09
     Carn
    0.09
    Activations Density 0.008%

    No Known Activations