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. 23-RESID-POST-AA
    6. 98249
    Prev
    Next
    INDEX
    Explanations

    positive energy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     silêncio
    -0.12
     silencio
    -0.12
     ضعف
    -0.10
    孤
    -0.10
     ужас
    -0.10
     dårlig
    -0.10
     ظلم
    -0.10
     कमजोर
    -0.10
     misog
    -0.09
     نقصان
    -0.09
    POSITIVE LOGITS
     lively
    0.39
     energetic
    0.34
     upbeat
    0.33
     enthusiastic
    0.33
     vibrant
    0.33
     joyful
    0.33
     enthusiasm
    0.32
     enthousiasme
    0.32
     cheerful
    0.32
     enthousiaste
    0.31
    Activations Density 0.359%

    No Known Activations