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. 77257
    Prev
    Next
    INDEX
    Explanations

    horizontal lines

    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
     putem
    -0.09
    /person
    -0.07
     Marathon
    -0.07
    ’import
    -0.07
     ambit
    -0.07
     Trung
    -0.07
     vrais
    -0.07
     bois
    -0.07
    Fore
    -0.07
    aż
    -0.07
    POSITIVE LOGITS
     replicas
    0.07
     welded
    0.07
    شت
    0.07
    rite
    0.07
     destiny
    0.07
    幸福
    0.07
    itar
    0.07
     ports
    0.07
    িত্র
    0.07
     replica
    0.07
    Activations Density 0.004%

    No Known Activations