© 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. 108454
    Prev
    Next
    INDEX
    Explanations

    convert to base ten

    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
    	sign
    -0.08
     crypt
    -0.08
     recycle
    -0.07
     cyan
    -0.07
     bied
    -0.07
     biomechanics
    -0.07
     exclude
    -0.07
     signing
    -0.07
    قطع
    -0.07
     sugar
    -0.07
    POSITIVE LOGITS
     숫
    0.09
    owanie
    0.09
    FI
    0.08
    .convert
    0.08
     число
    0.08
    ীক
    0.08
    erden
    0.08
    .Convert
    0.08
    Equivalent
    0.08
    isty
    0.08
    Activations Density 0.006%

    No Known Activations