© 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. 47098
    Prev
    Next
    INDEX
    Explanations

    I

    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
     Cunningham
    -0.09
     townhouse
    -0.08
    Tool
    -0.08
    _aug
    -0.08
    _future
    -0.08
    Rut
    -0.08
    ยัง
    -0.08
    stücke
    -0.07
     Rubin
    -0.07
     futura
    -0.07
    POSITIVE LOGITS
     whenever
    0.09
     afr
    0.08
     depended
    0.07
    ėj
    0.07
     أق
    0.07
     hodin
    0.07
    .Dep
    0.07
     Occasionally
    0.07
    යන්
    0.07
     analyzed
    0.06
    Activations Density 0.007%

    No Known Activations