Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 30518
    Prev
    Next
    INDEX
    Explanations

    practical

    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
     Национ
    -0.09
    ują
    -0.09
     национ
    -0.09
     بودن
    -0.08
     الأحيان
    -0.08
     Hewlett
    -0.08
    Nationality
    -0.08
     كلية
    -0.08
    Importance
    -0.08
     mons
    -0.08
    POSITIVE LOGITS
    措施
    0.13
     actionable
    0.12
     उपाय
    0.12
     concr
    0.11
     proactive
    0.11
     Maßnahmen
    0.11
     tiltak
    0.11
     कदम
    0.10
     maatregelen
    0.10
     doable
    0.10
    Activations Density 0.080%

    No Known Activations