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. 265
    Prev
    Next
    INDEX
    Explanations

    hostile work environment

    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
    仁
    -0.07
     убий
    -0.07
     \(
    -0.07
    兼
    -0.07
    クリ
    -0.07
     Hawk
    -0.07
     отч
    -0.07
     가져
    -0.07
    ூர
    -0.07
    utekano
    -0.07
    POSITIVE LOGITS
     sexu
    0.08
     Sexual
    0.08
     Actual
    0.08
     sexuelle
    0.07
     acet
    0.07
    Друг
    0.07
     أجزاء
    0.07
    Navigation
    0.07
     ptr
    0.07
     celular
    0.07
    Activations Density 0.003%

    No Known Activations