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. 49395
    Prev
    Next
    INDEX
    Explanations

    circuit protection

    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
    狼人
    -0.08
     costit
    -0.08
    Queryable
    -0.08
     spotify
    -0.08
    Documents
    -0.08
    wayne
    -0.08
    @login
    -0.08
     QRect
    -0.08
     CGRect
    -0.08
    _needed
    -0.08
    POSITIVE LOGITS
     protection
    0.11
     حفاظت
    0.11
     protections
    0.11
    保护
    0.11
     protective
    0.11
     protects
    0.10
     Protection
    0.10
     حماية
    0.09
     safety
    0.09
    检测
    0.09
    Activations Density 0.008%

    No Known Activations