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. 44163
    Prev
    Next
    INDEX
    Explanations

    waffle

    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
    群
    -0.08
     intelligence
    -0.08
     breathe
    -0.08
     covenant
    -0.08
    �
    -0.08
    尊
    -0.07
    德
    -0.07
    履
    -0.07
     aligning
    -0.07
     crowdfunding
    -0.07
    POSITIVE LOGITS
     Chair
    0.09
     бума
    0.08
     papel
    0.08
     chair
    0.08
     بنت
    0.08
    پي
    0.08
     spun
    0.08
     desserts
    0.08
     Honey
    0.08
     الهاتف
    0.08
    Activations Density 0.001%

    No Known Activations