© 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. 68683
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations/codes

    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
    .capitalize
    -0.09
     réputation
    -0.08
     reput
    -0.08
     Rey
    -0.08
    نظر
    -0.08
     Luxemburg
    -0.07
     чувство
    -0.07
     conséquences
    -0.07
     recalls
    -0.07
     induct
    -0.07
    POSITIVE LOGITS
    001
    0.13
    XXXXX
    0.11
    004
    0.11
    XXXX
    0.11
    030
    0.11
    006
    0.11
    005
    0.11
    000
    0.11
    XXXXXXXX
    0.10
    编号
    0.10
    Activations Density 0.043%

    No Known Activations