© 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. 91369
    Prev
    Next
    INDEX
    Explanations

    trace

    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
     COP
    -0.07
    ધાન
    -0.07
    DTO
    -0.07
     Responsive
    -0.07
     bankruptcy
    -0.07
    /c
    -0.07
    fone
    -0.07
     permission
    -0.07
     捕
    -0.07
    VO
    -0.07
    POSITIVE LOGITS
    原则
    0.08
     geothermal
    0.08
    入住
    0.08
     Unterkunft
    0.08
     vierde
    0.08
     offsets
    0.08
     ........
    0.08
     minimizing
    0.08
    距离
    0.08
    游客
    0.08
    Activations Density 0.005%

    No Known Activations