© 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. 23-RESID-POST-AA
    11. 49401
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
     perfe
    -0.09
     ial
    -0.08
     teenager
    -0.08
    /off
    -0.08
    /client
    -0.08
    -perfect
    -0.08
     equally
    -0.07
     flawlessly
    -0.07
     Teller
    -0.07
    icy
    -0.07
    POSITIVE LOGITS
     calcular
    0.09
     LI
    0.09
    =Math
    0.08
    會
    0.08
     LN
    0.08
    람
    0.08
     dhow
    0.08
     lidar
    0.08
     lia
    0.08
     obter
    0.08
    Activations Density 0.006%

    No Known Activations