© 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. 11-RESID-POST-AA
    11. 78458
    Prev
    Next
    INDEX
    Explanations

    Do/We

    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
    626
    -0.08
     dollars
    -0.08
    okuq
    -0.08
     GPA
    -0.07
     Überblick
    -0.07
     odn
    -0.07
     décider
    -0.07
     μ
    -0.07
    ukan
    -0.07
     Goal
    -0.07
    POSITIVE LOGITS
    避
    0.09
     vermijden
    0.09
     adhere
    0.08
     лиш
    0.08
     соблюдать
    0.08
    avoid
    0.08
    alternate
    0.08
    reme
    0.08
     avoid
    0.08
    避免
    0.08
    Activations Density 0.004%

    No Known Activations