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. 65691
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     jau
    -0.07
     progressive
    -0.07
    .arange
    -0.07
     construcción
    -0.07
    logue
    -0.07
     माय
    -0.07
     familiarize
    -0.07
     dream
    -0.07
    bildung
    -0.07
    构
    -0.07
    POSITIVE LOGITS
    /template
    0.08
    awah
    0.08
     differed
    0.08
    __[
    0.08
    alisco
    0.08
    ”)
    0.08
    ʻa
    0.08
     intraven
    0.08
    ’ın
    0.08
    ertal
    0.08
    Activations Density 0.007%

    No Known Activations