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. 15-RESID-POST-AA
    6. 19259
    Prev
    Next
    INDEX
    Explanations

    fairness

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curled
    -0.09
     Brot
    -0.09
    �菜
    -0.09
    /navigation
    -0.09
    wget
    -0.08
    住所
    -0.08
     unterwegs
    -0.08
    驻
    -0.08
    Adresse
    -0.08
    、电
    -0.08
    POSITIVE LOGITS
    公平
    0.18
     fairness
    0.17
     scoring
    0.15
    评分
    0.15
     ನ್ಯಾಯ
    0.14
     impartial
    0.14
     Bewert
    0.14
     объектив
    0.14
     equitable
    0.13
     fair
    0.13
    Activations Density 0.025%

    No Known Activations