© 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. 63895
    Prev
    Next
    INDEX
    Explanations

    cover

    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
     zapis
    -0.08
     Kod
    -0.08
     معرفة
    -0.08
    ایع
    -0.08
    wino
    -0.08
     واضحة
    -0.08
     inherently
    -0.08
    jonali
    -0.07
     fundamentally
    -0.07
     naturale
    -0.07
    POSITIVE LOGITS
     veneers
    0.10
     veneer
    0.10
    pane
    0.09
    板
    0.09
     harr
    0.09
    panelen
    0.08
    leaf
    0.08
    QP
    0.08
    罩
    0.08
    厂
    0.08
    Activations Density 0.023%

    No Known Activations