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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 130553
    Prev
    Next
    INDEX
    Explanations

    race outcomes

    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
     mita
    -0.09
     كمية
    -0.09
     соедин
    -0.08
     افز
    -0.08
     ortak
    -0.08
    :image
    -0.08
     hubby
    -0.08
    Tamb
    -0.08
     свойства
    -0.08
    טל
    -0.08
    POSITIVE LOGITS
     rankings
    0.16
     ranking
    0.15
    順位
    0.15
    排名
    0.14
    Ranking
    0.14
     Rankings
    0.14
    ranking
    0.14
     ranked
    0.13
    排行榜
    0.13
     winner
    0.13
    Activations Density 0.017%

    No Known Activations