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. 13023
    Prev
    Next
    INDEX
    Explanations

    部

    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
     Warm
    -0.09
    Warm
    -0.08
     bedside
    -0.08
     раз
    -0.08
    Arch
    -0.07
    Responder
    -0.07
    _embed
    -0.07
    450
    -0.07
    対応
    -0.07
     gastronom
    -0.07
    POSITIVE LOGITS
     workings
    0.11
     داخ
    0.08
     ناس
    0.08
     scooters
    0.07
     Fon
    0.07
    ப்
    0.07
     تستخدم
    0.07
     هڅ
    0.07
     intern
    0.07
     ری
    0.07
    Activations Density 0.007%

    No Known Activations