© 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. 29324
    Prev
    Next
    INDEX
    Explanations

    prime factorization

    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
     leisure
    -0.09
     immersion
    -0.08
     SATA
    -0.08
    offer
    -0.08
    (effect
    -0.07
    oulder
    -0.07
    روة
    -0.07
     accl
    -0.07
     Ego
    -0.07
     erect
    -0.07
    POSITIVE LOGITS
     crimes
    0.08
     fib
    0.08
     nguy
    0.08
     divisible
    0.08
     terdiri
    0.07
     evaluate
    0.07
    .tw
    0.07
     olub
    0.07
     ARC
    0.07
    ấm
    0.07
    Activations Density 0.034%

    No Known Activations