© 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. 111273
    Prev
    Next
    INDEX
    Explanations

    sports, kicking, catching, tackling

    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
    .UUID
    -0.08
     gour
    -0.07
     individual
    -0.07
    Each
    -0.07
    涵
    -0.07
     genetic
    -0.07
     spicy
    -0.07
     envers
    -0.07
     individuele
    -0.07
     feugiat
    -0.07
    POSITIVE LOGITS
     reclaim
    0.10
    Clean
    0.09
    catch
    0.09
    Cleanup
    0.09
    -clean
    0.09
     interception
    0.09
    clean
    0.08
    Caught
    0.08
     debris
    0.08
     Clean
    0.08
    Activations Density 0.022%

    No Known Activations