© 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. 6290
    Prev
    Next
    INDEX
    Explanations

    sklearn library

    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
     BH
    -0.09
    BH
    -0.08
    ():↵↵
    -0.08
    -
    -0.08
    .channel
    -0.08
    of
    -0.08
     قناة
    -0.08
    key
    -0.07
    ()`
    -0.07
     Draco
    -0.07
    POSITIVE LOGITS
    ็ง
    0.10
    ம்பர்
    0.09
     cumin
    0.08
     xmin
    0.08
    ದುಕ
    0.08
    _tbl
    0.08
    ிங்
    0.08
    못
    0.08
    െങ്ക
    0.08
    ်
    0.08
    Activations Density 0.000%

    No Known Activations