© 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. 23-RESID-POST-AA
    11. 50702
    Prev
    Next
    INDEX
    Explanations

    race/embrace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .lo
    -0.09
     LO
    -0.08
    _lo
    -0.08
     رهي
    -0.08
    lo
    -0.08
     gepl
    -0.08
    .bukkit
    -0.08
    /lib
    -0.07
    jih
    -0.07
     Block
    -0.07
    POSITIVE LOGITS
     embrace
    0.13
     amaze
    0.11
     race
    0.11
     races
    0.11
     chase
    0.10
     traced
    0.10
     tace
    0.10
     embraced
    0.10
     embracing
    0.10
    Trace
    0.10
    Activations Density 0.001%

    No Known Activations