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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23168
    Prev
    Next
    INDEX
    Explanations

    mathematical increase

    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
     HC
    -0.09
     acúst
    -0.08
    メール
    -0.08
    ೃ
    -0.08
    (Bundle
    -0.08
     ಮಾತ
    -0.08
    ಿಕ್ಕ
    -0.08
     ಕು
    -0.08
     ಕಡ
    -0.08
    退款
    -0.07
    POSITIVE LOGITS
    增长
    0.13
     grows
    0.13
     growth
    0.12
     বৃদ্ধি
    0.12
    creasing
    0.12
     increases
    0.12
     croissance
    0.12
     crecer
    0.12
     increasing
    0.11
     वाढ
    0.11
    Activations Density 0.058%

    No Known Activations