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. 52940
    Prev
    Next
    INDEX
    Explanations

    Extent

    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
     entdeckt
    -0.09
    知ら
    -0.08
    丸
    -0.08
     dikenal
    -0.08
    Trips
    -0.08
     erkannt
    -0.08
     revelations
    -0.07
    wise
    -0.07
     জানা
    -0.07
    オン
    -0.07
    POSITIVE LOGITS
     миним
    0.10
     Stu
    0.09
     Resultado
    0.08
     החלט
    0.08
     climat
    0.08
     Размер
    0.08
     decisiones
    0.08
     resultaat
    0.08
    决定
    0.08
    resultado
    0.08
    Activations Density 0.000%

    No Known Activations