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. 111686
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     Steiner
    -0.08
     weltweit
    -0.08
     glob
    -0.08
     nam
    -0.07
    .st
    -0.07
     letu
    -0.07
     upward
    -0.07
     doz
    -0.07
     hier
    -0.07
    Worldwide
    -0.07
    POSITIVE LOGITS
     Efficiency
    0.09
     eficiencia
    0.09
     Normalize
    0.09
    فاءة
    0.09
     numerator
    0.08
     сопр
    0.08
     Ի
    0.08
     ժ
    0.08
    Tint
    0.08
    Normalize
    0.08
    Activations Density 0.035%

    No Known Activations