© 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. 45278
    Prev
    Next
    INDEX
    Explanations

    JSON handling in code

    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
     design
    -0.08
     schedule
    -0.08
    Schedule
    -0.08
    _schedule
    -0.08
    _dis
    -0.07
    dis
    -0.07
     freue
    -0.07
     çat
    -0.07
     dispenser
    -0.07
     freuen
    -0.07
    POSITIVE LOGITS
     ابتدا
    0.09
     Temporary
    0.09
    Temporary
    0.09
     intermedi
    0.08
    arshal
    0.08
     temporary
    0.08
     intermediary
    0.08
     intermediate
    0.08
     сначала
    0.08
     RTT
    0.08
    Activations Density 0.004%

    No Known Activations