© 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. 5828
    Prev
    Next
    INDEX
    Explanations

    Before and after comparisons

    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
    حسب
    -0.07
    _LO
    -0.07
     builtin
    -0.07
     cải
    -0.07
    nda
    -0.07
    SOR
    -0.07
    714
    -0.07
     banana
    -0.07
    契
    -0.07
     farko
    -0.07
    POSITIVE LOGITS
    ù
    0.08
    ุม
    0.07
     neb
    0.07
    юш
    0.07
    ustos
    0.07
    象
    0.07
     vivimos
    0.07
     migraines
    0.07
    
    0.07
     назад
    0.07
    Activations Density 0.000%

    No Known Activations