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. 112212
    Prev
    Next
    INDEX
    Explanations

    narratives and conversations

    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
    ↵  ↵
    -0.09
      ↵  ↵
    -0.09
     ↵  ↵
    -0.08
    ↵↵  ↵
    -0.07
    クロ
    -0.07
     Kreat
    -0.07
    ,…↵↵
    -0.07
    -dé
    -0.07
      ↵↵  ↵↵
    -0.07
    :_
    -0.07
    POSITIVE LOGITS
    0.07
     Benn
    0.07
    Rev
    0.07
     देकर
    0.07
    oni
    0.07
     बंग
    0.07
    truncate
    0.07
    ψεις
    0.07
    Dining
    0.07
    rim
    0.07
    Activations Density 0.144%

    No Known Activations