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. 30634
    Prev
    Next
    INDEX
    Explanations

    Procedures

    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
     hybrid
    -0.10
    Hybrid
    -0.09
     Hybrid
    -0.09
    hy
    -0.08
     hybrids
    -0.08
     Hy
    -0.08
     hybr
    -0.07
     blush
    -0.07
     dros
    -0.07
     híbr
    -0.07
    POSITIVE LOGITS
    Sent
    0.08
    	Intent
    0.08
    ển
    0.08
    �
    0.08
    :《
    0.08
     bagaimana
    0.08
    CCC
    0.08
     Ensuite
    0.08
    <>();
    ↵
    0.08
     columnas
    0.08
    Activations Density 0.000%

    No Known Activations