© 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. 70300
    Prev
    Next
    INDEX
    Explanations

    error handling (code)

    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
    hiq
    -0.07
    .Value
    -0.07
     Av
    -0.07
     advantageous
    -0.07
     IVA
    -0.07
     elbows
    -0.07
     mor
    -0.07
     sağlay
    -0.07
     Advantage
    -0.07
    Automation
    -0.07
    POSITIVE LOGITS
     winding
    0.09
     fouten
    0.09
    Throwable
    0.09
    ascular
    0.09
     ошиб
    0.08
     Throwable
    0.08
    attanooga
    0.08
    adde
    0.08
     forgot
    0.08
     faulty
    0.08
    Activations Density 0.001%

    No Known Activations