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

    Neuronpedia

    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. 26233
    Prev
    Next
    INDEX
    Explanations

    size

    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
     ykn
    -0.09
     scegliere
    -0.08
     ịch
    -0.08
     coisa
    -0.08
     rů
    -0.08
    Ae
    -0.07
    -risk
    -0.07
    ()),↵
    -0.07
     baskets
    -0.07
    Files
    -0.07
    POSITIVE LOGITS
     анық
    0.08
     اهمیت
    0.08
     blat
    0.07
     alike
    0.07
     längst
    0.07
     numerical
    0.07
     expresa
    0.07
     explíc
    0.07
     обязательно
    0.07
     numeral
    0.07
    Activations Density 0.000%

    No Known Activations