© 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. 64187
    Prev
    Next
    INDEX
    Explanations

    poly

    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
     Thai
    -0.08
     بص
    -0.08
     bulls
    -0.08
     mynd
    -0.08
     المال
    -0.08
     আনন্দ
    -0.08
    赏
    -0.08
     Bangkok
    -0.08
     تف
    -0.08
     مرب
    -0.07
    POSITIVE LOGITS
    <!--[
    0.11
    fallback
    0.10
     shim
    0.10
    compat
    0.10
     backwards
    0.10
     poly
    0.09
     oudere
    0.09
     compatibility
    0.09
     backward
    0.09
    _poly
    0.09
    Activations Density 0.009%

    No Known Activations