© 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. 95055
    Prev
    Next
    INDEX
    Explanations

    navigation and migration

    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
     Showing
    -0.08
    çons
    -0.08
    Showing
    -0.08
     Unlimited
    -0.07
     showing
    -0.07
     onderwijs
    -0.07
     tarifas
    -0.07
    教育
    -0.07
     Educação
    -0.07
     enlightening
    -0.07
    POSITIVE LOGITS
     Navigation
    0.08
    導航
    0.08
    !',↵
    0.08
    !).
    0.08
    !),
    0.08
     polarity
    0.08
     exile
    0.08
    metics
    0.08
    Navigation
    0.08
    .PI
    0.08
    Activations Density 0.011%

    No Known Activations