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. 111893
    Prev
    Next
    INDEX
    Explanations

    Hooks to draw attention

    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
    ῦ
    -0.09
     Styles
    -0.08
    ubi
    -0.08
    .Metro
    -0.07
     Style
    -0.07
    %d
    -0.07
     Semester
    -0.07
     standardized
    -0.07
    规律
    -0.07
     реализ
    -0.07
    POSITIVE LOGITS
     Aufmerksamkeit
    0.11
     uwagę
    0.10
     внимания
    0.10
     внимание
    0.10
     perhatian
    0.10
     attenzione
    0.09
     disbelief
    0.09
    Attention
    0.09
     atenção
    0.09
     attention
    0.09
    Activations Density 0.028%

    No Known Activations