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. 58879
    Prev
    Next
    INDEX
    Explanations

    plant photosynthesis adaptations

    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
     jobject
    -0.09
     refere
    -0.08
    Psych
    -0.08
     Benchmark
    -0.08
    headed
    -0.08
     Visualization
    -0.08
     benchmark
    -0.08
    Visualizer
    -0.08
    abelle
    -0.08
    -skilled
    -0.08
    POSITIVE LOGITS
     gradients
    0.09
    .defer
    0.08
     पिछ
    0.08
     ночью
    0.08
     cues
    0.08
     प्रतिक्र
    0.07
     पश्चिम
    0.07
     noct
    0.07
    _backward
    0.07
     cranes
    0.07
    Activations Density 0.001%

    No Known Activations