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. 8427
    Prev
    Next
    INDEX
    Explanations

    employees

    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
    态
    -0.08
     даты
    -0.07
    יכול
    -0.07
     עולם
    -0.07
    יתוף
    -0.07
     trituradora
    -0.07
    משך
    -0.07
    რული
    -0.07
    ಗಾರ
    -0.07
    ATAR
    -0.07
    POSITIVE LOGITS
     proportion
    0.09
     نسبة
    0.08
    ozy
    0.08
     mothers
    0.08
    �s
    0.07
     femmes
    0.07
     mobs
    0.07
     MOB
    0.07
     hommes
    0.07
    695
    0.07
    Activations Density 0.021%

    No Known Activations