© 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 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. 112711
    Prev
    Next
    INDEX
    Explanations

    ==

    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
     Szen
    -0.08
     modernen
    -0.08
    ve
    -0.08
    .UPDATE
    -0.07
    w
    -0.07
     modeled
    -0.07
    awg
    -0.07
    .Management
    -0.07
    Analysis
    -0.07
     outward
    -0.07
    POSITIVE LOGITS
     deliberately
    0.08
     intentionally
    0.08
    خصوص
    0.08
     selectively
    0.08
    限定
    0.07
     selective
    0.07
     специалистов
    0.07
     serialize
    0.07
    (history
    0.07
     supaya
    0.07
    Activations Density 0.004%

    No Known Activations