© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95314
    Prev
    Next
    INDEX
    Explanations

    machine learning steps

    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
     filled
    -0.10
    漫畫
    -0.09
     bunker
    -0.09
     fifo
    -0.09
    Traversal
    -0.09
     Filled
    -0.09
     crane
    -0.08
     cnc
    -0.08
     gevuld
    -0.08
     cw
    -0.08
    POSITIVE LOGITS
     preprocessing
    0.12
    性能
    0.12
     sklearn
    0.12
     optimizing
    0.12
    优化
    0.12
     optimization
    0.12
     supervised
    0.11
     Dataset
    0.11
     Optimization
    0.11
    _optimizer
    0.11
    Activations Density 0.024%

    No Known Activations