© 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. 69655
    Prev
    Next
    INDEX
    Explanations

    numerical or hyphen

    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
     correctly
    -0.08
    .Te
    -0.08
     patch
    -0.07
    .quant
    -0.07
    Ster
    -0.07
     eq
    -0.07
    564
    -0.07
     cloak
    -0.07
    .Temp
    -0.07
     правильно
    -0.07
    POSITIVE LOGITS
     adulter
    0.09
     Jahrhundert
    0.08
     adverse
    0.08
    terminate
    0.08
    ječ
    0.08
     yarad
    0.07
     Yukon
    0.07
    šo
    0.07
     suspected
    0.07
     Empfehl
    0.07
    Activations Density 0.001%

    No Known Activations