© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48047
    Prev
    Next
    INDEX
    Explanations

    inclusion-exclusion principle

    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
     Aurora
    -0.10
     trader
    -0.09
     cryptocurrency
    -0.08
    Trader
    -0.08
     крип
    -0.08
     Whisper
    -0.08
     aftermarket
    -0.08
    ponent
    -0.08
    cryption
    -0.08
     Trader
    -0.08
    POSITIVE LOGITS
    count
    0.11
    人数
    0.11
    subtract
    0.11
     subtract
    0.10
     counts
    0.10
     counting
    0.10
     count
    0.10
    Subtract
    0.10
    .Count
    0.10
     populations
    0.10
    Activations Density 0.051%

    No Known Activations