© 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. 23-RESID-POST-AA
    11. 48219
    Prev
    Next
    INDEX
    Explanations

    onic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мач
    -0.08
     Sohn
    -0.08
    egger
    -0.08
     kth
    -0.08
     Thc
    -0.08
    664
    -0.08
     Disclaimer
    -0.08
    534
    -0.08
    ıkları
    -0.08
     väga
    -0.08
    POSITIVE LOGITS
     shifts
    0.09
     Front
    0.09
     Riders
    0.08
     Forces
    0.08
     stort
    0.08
     Shuffle
    0.08
     Rush
    0.08
     Robo
    0.07
     Lost
    0.07
     parallels
    0.07
    Activations Density 0.001%

    No Known Activations