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. 102896
    Prev
    Next
    INDEX
    Explanations

    coding theory

    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
     Chinatown
    -0.08
     immigrant
    -0.08
    vio
    -0.08
    工
    -0.08
     дед
    -0.08
     maan
    -0.08
    班
    -0.08
     diner
    -0.07
    �
    -0.07
     سي
    -0.07
    POSITIVE LOGITS
    benchmark
    0.10
     Benchmark
    0.09
     benchmark
    0.09
    Benchmark
    0.09
     benchmarks
    0.09
     studied
    0.09
     Exact
    0.09
    Exact
    0.08
     benchmarking
    0.08
    uyla
    0.08
    Activations Density 0.017%

    No Known Activations