© 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. 91647
    Prev
    Next
    INDEX
    Explanations

    tied, same

    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
    mið
    -0.08
     beaucoup
    -0.08
    .K
    -0.07
     firmly
    -0.07
     creepy
    -0.07
    she
    -0.07
    跟
    -0.07
    вр
    -0.07
    .Anal
    -0.07
    .mvp
    -0.07
    POSITIVE LOGITS
     empate
    0.11
    -height
    0.08
     igualdad
    0.08
     offensichtlich
    0.08
    unlikely
    0.08
     widths
    0.08
     సమయంలో
    0.08
     হলে
    0.08
    ,width
    0.08
    Lowest
    0.08
    Activations Density 0.012%

    No Known Activations