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. 23374
    Prev
    Next
    INDEX
    Explanations

    来

    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
     growth
    -0.09
     성장
    -0.08
     propensity
    -0.08
    Ramp
    -0.08
     crescimento
    -0.08
     dedication
    -0.08
     margin
    -0.08
    growth
    -0.07
     sorg
    -0.07
     margins
    -0.07
    POSITIVE LOGITS
     semaphore
    0.12
    Semaphore
    0.12
     Semaphore
    0.12
    aphore
    0.12
     recursos
    0.11
    许可证
    0.10
    .available
    0.10
    _resources
    0.10
     നിയന്ത്ര
    0.10
    资源
    0.10
    Activations Density 0.005%

    No Known Activations