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. 112749
    Prev
    Next
    INDEX
    Explanations

    absurdity and surreal situations

    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
     ansiedade
    -0.08
     badan
    -0.07
     ubr
    -0.07
     contrato
    -0.07
     consciente
    -0.07
     refin
    -0.07
    隐藏
    -0.07
     tir
    -0.07
     kao
    -0.07
    検索
    -0.06
    POSITIVE LOGITS
     পরিস্থিত
    0.11
     اللقاء
    0.10
     صورتحال
    0.10
     unusual
    0.10
     ঘট
    0.09
     необы
    0.09
    נ
    0.09
     surreal
    0.09
     проис
    0.09
    情况
    0.09
    Activations Density 0.037%

    No Known Activations