© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69631
    Prev
    Next
    INDEX
    Explanations

    French Revolution

    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
     alkalmaz
    -0.11
    ย้อน
    -0.09
    dracht
    -0.08
    ថ
    -0.08
     hosped
    -0.08
     aussch
    -0.08
    (min
    -0.08
    үрүш
    -0.07
     melod
    -0.07
    odnev
    -0.07
    POSITIVE LOGITS
     نشده
    0.09
    -none
    0.08
     NULL
    0.08
     NON
    0.08
     गरीब
    0.07
     non
    0.07
     não
    0.07
    NON
    0.07
     cave
    0.07
     Não
    0.07
    Activations Density 0.003%

    No Known Activations