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. 43391
    Prev
    Next
    INDEX
    Explanations

    experiment

    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
    annu
    -0.11
     несов
    -0.09
     collectibles
    -0.09
     failing
    -0.09
     erinnert
    -0.08
     Whit
    -0.08
     conspiracy
    -0.08
     مفهوم
    -0.08
    藏
    -0.08
     احتمال
    -0.08
    POSITIVE LOGITS
    benchmark
    0.13
     benchmarking
    0.13
     benchmark
    0.13
     demonstrating
    0.12
     demonstrated
    0.12
    Benchmark
    0.12
    Simulation
    0.12
     benchmarks
    0.11
    测试
    0.11
     demostr
    0.11
    Activations Density 0.025%

    No Known Activations