© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48541
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     mức
    -0.08
    α
    -0.08
    .schedule
    -0.08
     interf
    -0.07
     scheduling
    -0.07
     affected
    -0.07
    .init
    -0.07
     blazing
    -0.07
    imbal
    -0.07
    .Resource
    -0.07
    POSITIVE LOGITS
    合法
    0.09
     voyeur
    0.09
     legit
    0.09
     legalized
    0.09
    /legal
    0.08
     COPYING
    0.08
    argout
    0.08
    (EXIT
    0.08
    _LONG
    0.08
     Verl
    0.08
    Activations Density 0.000%

    No Known Activations