© 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. 69407
    Prev
    Next
    INDEX
    Explanations

    moderate

    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
     tightly
    -0.08
    grain
    -0.08
     कीमत
    -0.07
     Zach
    -0.07
     naissance
    -0.07
    upu
    -0.07
    shade
    -0.07
     Kathryn
    -0.07
    字号
    -0.07
     väg
    -0.07
    POSITIVE LOGITS
     depression
    0.10
    .column
    0.09
    [col
    0.08
     illnesses
    0.08
     onward
    0.08
     운동
    0.08
    ,col
    0.08
     Depression
    0.08
     cord
    0.08
    .col
    0.08
    Activations Density 0.005%

    No Known Activations