© 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 EvalsExportsinterp-engineNEWAPI 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. 70153
    Prev
    Next
    INDEX
    Explanations

    Lines and intersections

    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
     જામ
    -0.08
     primes
    -0.08
     gcd
    -0.07
     prime
    -0.07
    .ec
    -0.07
     verifying
    -0.07
     sab
    -0.07
     <>
    -0.07
     Erd
    -0.07
     setter
    -0.07
    POSITIVE LOGITS
     atrop
    0.09
    řízení
    0.09
     cylindrical
    0.09
     neop
    0.08
     Interrupted
    0.08
     lateral
    0.08
     roadway
    0.08
    ories
    0.08
     Motorcycle
    0.08
     Rotary
    0.08
    Activations Density 0.009%

    No Known Activations