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. 49313
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     сериал
    -0.09
     ROS
    -0.08
    neck
    -0.08
     thermal
    -0.07
    richt
    -0.07
    涓
    -0.07
    驻
    -0.07
     Syr
    -0.07
     Serializer
    -0.07
     aboard
    -0.07
    POSITIVE LOGITS
    塔
    0.09
     factual
    0.08
     explanation
    0.08
    लं
    0.08
     Conclusions
    0.08
    .logic
    0.08
     conclusion
    0.08
     explanations
    0.08
    .default
    0.08
     conclusions
    0.07
    Activations Density 0.005%

    No Known Activations