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. 43285
    Prev
    Next
    INDEX
    Explanations

    Vowel pronunciation

    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
    米奇
    -0.08
     milestones
    -0.08
     vandal
    -0.08
     slaughter
    -0.08
    消防
    -0.07
    所
    -0.07
    交易
    -0.07
     allocations
    -0.07
    chent
    -0.07
     endorsements
    -0.07
    POSITIVE LOGITS
    elib
    0.09
     ശ്ര
    0.08
     кав
    0.08
     bewusst
    0.08
    avadoc
    0.08
     பழ
    0.08
     Unsupported
    0.08
     behave
    0.08
     afin
    0.08
     sval
    0.08
    Activations Density 0.006%

    No Known Activations