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. 98438
    Prev
    Next
    INDEX
    Explanations

    everyday

    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
     دائم
    -0.09
     everytime
    -0.09
     Always
    -0.09
     always
    -0.09
    每日
    -0.08
    每天
    -0.08
     हमेशा
    -0.08
     всегда
    -0.08
     siempre
    -0.08
     traditionellen
    -0.08
    POSITIVE LOGITS
     जिंदगी
    0.15
     life
    0.15
    생활
    0.14
     həy
    0.14
    生活
    0.13
    -life
    0.13
     زندگی
    0.13
     hassles
    0.13
     জীব
    0.12
     жизни
    0.12
    Activations Density 0.032%

    No Known Activations