© 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. 54932
    Prev
    Next
    INDEX
    Explanations

    Mathematics

    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
     सुध
    -0.09
     Ami
    -0.08
     abgest
    -0.08
     Amerik
    -0.08
     જીવ
    -0.08
     ingeniería
    -0.07
     cilvē
    -0.07
     Shel
    -0.07
     grø
    -0.07
     História
    -0.07
    POSITIVE LOGITS
     fisher
    0.08
     caval
    0.07
    deren
    0.07
     που
    0.07
     vpn
    0.07
     dispute
    0.07
    ,Y
    0.07
    _named
    0.07
    gulp
    0.07
     Magazine
    0.07
    Activations Density 0.126%

    No Known Activations