© 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. 113381
    Prev
    Next
    INDEX
    Explanations

    rational

    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
     teamwork
    -0.08
     contributed
    -0.08
    ണ്ട്
    -0.08
     clarified
    -0.08
     shampoo
    -0.07
     تیم
    -0.07
    stå
    -0.07
     clarification
    -0.07
     spherical
    -0.07
    Rear
    -0.07
    POSITIVE LOGITS
    utik
    0.09
     enumerable
    0.08
     irrational
    0.08
     innumer
    0.08
    的网址
    0.08
     utak
    0.08
     ration
    0.08
     finer
    0.08
     irr
    0.08
     Rational
    0.08
    Activations Density 0.009%

    No Known Activations