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. 12238
    Prev
    Next
    INDEX
    Explanations

    code

    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
    abet
    -0.09
     vect
    -0.08
     scientists
    -0.08
     intellectually
    -0.08
     resentment
    -0.08
     õpp
    -0.08
    dert
    -0.08
     intolerance
    -0.08
     limbs
    -0.08
    	Vector
    -0.08
    POSITIVE LOGITS
     Twig
    0.10
    .twig
    0.09
     CHtml
    0.09
    ="{{
    0.09
     rendered
    0.09
     ?>↵↵
    0.09
     htmlspecialchars
    0.09
    Twig
    0.09
     ?:
    0.09
     {%
    0.09
    Activations Density 0.008%

    No Known Activations