Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53923
    Prev
    Next
    INDEX
    Explanations

    traffic

    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
    -ul
    -0.08
    Rue
    -0.08
    Bass
    -0.07
    Realm
    -0.07
    алау
    -0.07
    Superclass
    -0.07
    crop
    -0.07
    Neue
    -0.07
     breastfeeding
    -0.07
    alim
    -0.07
    POSITIVE LOGITS
     traffic
    0.10
     casualties
    0.10
    traffic
    0.09
     തട
    0.09
     congestion
    0.09
    交通
    0.09
     fatalities
    0.09
    安排
    0.08
     المرور
    0.08
     congest
    0.08
    Activations Density 0.011%

    No Known Activations