© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44887
    Prev
    Next
    INDEX
    Explanations

    administration/gestion

    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
     والأس
    -0.08
     asseg
    -0.08
     olup
    -0.08
     Puffy
    -0.08
     modi
    -0.08
     ASK
    -0.08
     senti
    -0.08
     ಕೇಳ
    -0.08
    ্বর
    -0.08
     منها
    -0.08
    POSITIVE LOGITS
    管理
    0.11
     관리
    0.10
     overseeing
    0.09
     басқар
    0.09
     managerial
    0.09
     affairs
    0.09
    控
    0.08
     oversee
    0.08
     gestão
    0.08
    Gestion
    0.08
    Activations Density 0.084%

    No Known Activations