© 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. 26417
    Prev
    Next
    INDEX
    Explanations

    maps and navigation

    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
     volleyball
    -0.08
     decadent
    -0.08
    remarks
    -0.08
    舒服
    -0.08
    andbox
    -0.08
     oysters
    -0.08
     torture
    -0.07
     demean
    -0.07
    okk
    -0.07
    pressive
    -0.07
    POSITIVE LOGITS
     GPS
    0.17
    導航
    0.14
    GPS
    0.14
    导航
    0.14
     gps
    0.14
    /navigation
    0.13
     itinerary
    0.13
     안내
    0.13
    -navigation
    0.13
     маршрут
    0.13
    Activations Density 0.061%

    No Known Activations