© 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. 95822
    Prev
    Next
    INDEX
    Explanations

    or

    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
    helves
    -0.09
    creens
    -0.08
    shield
    -0.08
    cx
    -0.08
    ुओं
    -0.08
    gsm
    -0.08
    cmd
    -0.07
     Laboratories
    -0.07
    roduction
    -0.07
     Petersen
    -0.07
    POSITIVE LOGITS
     рез
    0.08
     resort
    0.08
     Liv
    0.07
     будь
    0.07
     उपाय
    0.07
     звер
    0.07
     Glory
    0.07
    naments
    0.07
     الحصول
    0.07
    %">↵
    0.07
    Activations Density 0.006%

    No Known Activations