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. 29894
    Prev
    Next
    INDEX
    Explanations

    Texas

    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
    衣
    -0.10
    üse
    -0.09
    打印
    -0.09
     printers
    -0.09
    书
    -0.09
     coats
    -0.08
    coat
    -0.08
    箭
    -0.08
     нос
    -0.08
    链
    -0.08
    POSITIVE LOGITS
     Matlab
    0.09
     mo
    0.08
     SK
    0.08
     southern
    0.07
     benchmark
    0.07
    ingar
    0.07
    Benchmark
    0.07
     Benchmark
    0.07
    夏
    0.07
     outages
    0.07
    Activations Density 0.011%

    No Known Activations