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. 90355
    Prev
    Next
    INDEX
    Explanations

    norms

    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
     vantage
    -0.09
     turmoil
    -0.08
     glimps
    -0.08
    🏻
    -0.08
    🏼
    -0.08
     সাম
    -0.08
     Anytime
    -0.07
     níl
    -0.07
    _Table
    -0.07
    gran
    -0.07
    POSITIVE LOGITS
    事項
    0.09
    规范
    0.08
    Violation
    0.08
    航
    0.08
    ங்களை
    0.07
     infring
    0.07
     Viol
    0.07
     Buchanan
    0.07
     Kun
    0.07
    /pr
    0.07
    Activations Density 0.007%

    No Known Activations