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. 112986
    Prev
    Next
    INDEX
    Explanations

    leaf

    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
     आकार
    -0.08
    population
    -0.08
     населения
    -0.08
     mousse
    -0.07
     frosting
    -0.07
     makeover
    -0.07
    fläche
    -0.07
    -0.07
     Y
    -0.07
     Kanal
    -0.07
    POSITIVE LOGITS
     спут
    0.09
    Opened
    0.09
     opened
    0.09
    开始
    0.08
    ერბ
    0.08
    endants
    0.08
    .Elapsed
    0.08
     verjaardag
    0.08
     Aquesta
    0.08
     cloves
    0.08
    Activations Density 0.003%

    No Known Activations