Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 53977
    Prev
    Next
    INDEX
    Explanations

    reflection

    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
     initiatives
    -0.08
    kill
    -0.08
     win
    -0.07
     Currency
    -0.07
     Workers
    -0.07
     hemorr
    -0.07
    wins
    -0.07
     Super
    -0.07
    access
    -0.07
     Supplement
    -0.07
    POSITIVE LOGITS
     angled
    0.09
     makina
    0.09
     slit
    0.09
    矩
    0.09
     laws
    0.09
    辉
    0.09
     saka
    0.09
     piedras
    0.09
    本站
    0.09
     symmetrical
    0.09
    Activations Density 0.005%

    No Known Activations