© 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. 7-RESID-POST-AA
    11. 1340
    Prev
    Next
    INDEX
    Explanations

    payment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manufacturing
    -0.09
     renewable
    -0.09
     Renewable
    -0.08
     Manufacturing
    -0.08
     subterr
    -0.08
    Bild
    -0.08
     Bildung
    -0.07
     diaspora
    -0.07
    .identity
    -0.07
     freshwater
    -0.07
    POSITIVE LOGITS
     etiquette
    0.10
     restaurant
    0.10
    Restaurant
    0.09
    餐
    0.09
     indien
    0.09
     diners
    0.09
     cari
    0.08
     desserts
    0.08
     brunch
    0.08
    'hôtel
    0.08
    Activations Density 0.021%

    No Known Activations