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. 120461
    Prev
    Next
    INDEX
    Explanations

    Korea

    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
     decis
    -0.07
     yogurt
    -0.07
    ,opt
    -0.07
    贷
    -0.07
     thanksgiving
    -0.07
     іст
    -0.07
     undone
    -0.07
     foresee
    -0.07
     аллер
    -0.07
     vou
    -0.07
    POSITIVE LOGITS
    spannung
    0.09
     propaganda
    0.09
     Cambodia
    0.08
    �
    0.08
    wab
    0.08
    हे
    0.08
    企
    0.08
     sév
    0.08
     Extremely
    0.08
    jør
    0.08
    Activations Density 0.006%

    No Known Activations