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. 11-RESID-POST-AA
    6. 88212
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions

    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
    avet
    -0.09
     armor
    -0.08
     VECTOR
    -0.08
    icaid
    -0.08
     bombs
    -0.08
     nasional
    -0.08
     nationalism
    -0.08
    _BITMAP
    -0.08
     Mask
    -0.08
     dimensión
    -0.08
    POSITIVE LOGITS
     monoton
    0.09
     stric
    0.09
    禁止
    0.08
     consecutive
    0.08
     backward
    0.08
     slightly
    0.08
     subir
    0.08
    Backward
    0.08
    �
    0.08
     monot
    0.08
    Activations Density 0.024%

    No Known Activations