© 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. 31010
    Prev
    Next
    INDEX
    Explanations

    math/sets

    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
    .interpolate
    -0.08
     তুলে
    -0.08
    展开
    -0.08
    
    -0.07
    ografia
    -0.07
    .ie
    -0.07
     Classe
    -0.07
    .fire
    -0.07
    .refresh
    -0.07
    .eql
    -0.07
    POSITIVE LOGITS
     meets
    0.11
     meet
    0.10
     Meets
    0.10
     ×
    0.09
     divisible
    0.08
     ۽
    0.08
     અને
    0.08
    avity
    0.08
    且
    0.08
    AND
    0.08
    Activations Density 0.099%

    No Known Activations