© 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. 108771
    Prev
    Next
    INDEX
    Explanations

    line

    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
     SWOT
    -0.08
     emergencies
    -0.07
     Eth
    -0.07
    _lat
    -0.07
     Memories
    -0.07
     Disorders
    -0.07
    _trials
    -0.07
     см
    -0.07
    sev
    -0.07
    POSITIVE LOGITS
    াফ
    0.09
     commented
    0.09
    রাস
    0.09
    Initializing
    0.09
     لائن
    0.08
     ಸಾಲ
    0.08
    Rd
    0.08
     объявления
    0.08
    enea
    0.08
     വര
    0.08
    Activations Density 0.007%
    No Known Activations