Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43812
    Prev
    Next
    INDEX
    Explanations

    90

    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
     Hy
    -0.08
     precisión
    -0.08
     conta
    -0.08
     Bundes
    -0.07
     참고
    -0.07
    atora
    -0.07
     telef
    -0.07
     Telefonnummer
    -0.07
    ukt
    -0.07
     precisão
    -0.07
    POSITIVE LOGITS
    万能
    0.09
    递
    0.08
     सार्व
    0.08
    0.08
     Graves
    0.08
    循环
    0.07
     repeats
    0.07
     rotations
    0.07
     advancements
    0.07
     Organizational
    0.07
    Activations Density 0.005%

    No Known Activations