© 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. 110504
    Prev
    Next
    INDEX
    Explanations

    advertising descriptions

    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
     sigma
    -0.11
     Sigma
    -0.09
    sigma
    -0.09
    Sigma
    -0.09
     vector
    -0.08
     Σ
    -0.08
    .math
    -0.07
    /flutter
    -0.07
     present
    -0.07
    _sigma
    -0.07
    POSITIVE LOGITS
     эффектив
    0.09
    -important
    0.09
    important
    0.09
     précieux
    0.09
     тиімді
    0.09
     disgr
    0.08
     эстет
    0.08
     воспит
    0.08
    ，提高
    0.08
     bijna
    0.08
    Activations Density 0.737%

    No Known Activations