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. 15-RESID-POST-AA
    6. 19168
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jennifer
    -0.09
    ,but
    -0.09
    Anyway
    -0.08
    Однако
    -0.08
    ...).
    -0.08
    :");
    ↵
    -0.08
     juhul
    -0.08
    .Please
    -0.08
    。如果
    -0.08
    しかし
    -0.08
    POSITIVE LOGITS
     ↵↵
    0.17
     (
    0.15
    	↵↵
    0.14
      ↵↵
    0.13
     .↵↵
    0.13
    
↵↵
    0.13
    }↵↵
    0.13
    %↵↵
    0.12
    ۔↵↵
    0.12
     ↵
    0.12
    Activations Density 0.103%

    No Known Activations