© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99179
    Prev
    Next
    INDEX
    Explanations

    nurse

    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
     billion
    -0.08
     siècles
    -0.08
    自由
    -0.08
    ∞
    -0.08
     trillion
    -0.08
     centuries
    -0.08
     billions
    -0.07
    ัม
    -0.07
     ölç
    -0.07
     milliards
    -0.07
    POSITIVE LOGITS
     ઘરે
    0.08
     staffed
    0.08
     தலைவர்
    0.08
     stuffed
    0.08
    门
    0.08
    主任
    0.08
    -now
    0.08
    uyobozi
    0.08
    /head
    0.08
    門
    0.08
    Activations Density 0.008%

    No Known Activations