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. 58948
    Prev
    Next
    INDEX
    Explanations

    blender

    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
     passion
    -0.07
     Mat
    -0.07
     mat
    -0.07
     cold
    -0.07
    IVAL
    -0.07
     να
    -0.07
     ללמוד
    -0.07
     விள
    -0.07
    Wear
    -0.07
     Ker
    -0.07
    POSITIVE LOGITS
     результатов
    0.08
     bedside
    0.08
     рест
    0.08
    ických
    0.08
     операций
    0.08
     результата
    0.08
     решений
    0.08
     debajo
    0.08
     имеются
    0.08
     після
    0.08
    Activations Density 0.003%

    No Known Activations