© 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. 69096
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    empot
    -0.09
     ஆனால்
    -0.09
     لكنها
    -0.08
     Dentistry
    -0.08
     секун
    -0.08
     czyli
    -0.08
     ಆದರೆ
    -0.08
    DED
    -0.08
    த
    -0.08
    forcer
    -0.08
    POSITIVE LOGITS
     otev
    0.08
     откры
    0.08
     open
    0.08
    勿
    0.07
     reachable
    0.07
     opened
    0.07
     atento
    0.07
    0.07
     തുറ
    0.07
     nauw
    0.07
    Activations Density 0.012%
    No Known Activations