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. 58942
    Prev
    Next
    INDEX
    Explanations

    extra

    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
    “
    -0.08
    Iter
    -0.08
    Am
    -0.08
     toman
    -0.08
     approximation
    -0.07
     Am
    -0.07
     dieron
    -0.07
    ptive
    -0.07
    Iterations
    -0.07
    Þ
    -0.07
    POSITIVE LOGITS
     clang
    0.10
     Clean
    0.09
     साफ
    0.08
     sạch
    0.08
     '*.
    0.08
     LVS
    0.08
     clean
    0.08
    潔
    0.08
    clang
    0.08
     gcc
    0.08
    Activations Density 0.000%

    No Known Activations