© 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. 69358
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    Abi
    -0.09
     arqu
    -0.08
     UCLA
    -0.08
     PAC
    -0.08
     любит
    -0.08
    Rel
    -0.08
    RIS
    -0.07
    uar
    -0.07
    :str
    -0.07
    ывает
    -0.07
    POSITIVE LOGITS
     nemen
    0.08
     galaxies
    0.08
    合わせ
    0.08
    ^{-
    0.08
    油
    0.08
    евар
    0.08
     során
    0.07
    とも
    0.07
    -ons
    0.07
     Composition
    0.07
    Activations Density 0.050%

    No Known Activations