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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48131
    Prev
    Next
    INDEX
    Explanations

    case

    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
     veranderingen
    -0.08
     Laurel
    -0.08
     Chick
    -0.08
     Williams
    -0.08
     assent
    -0.08
     COLORS
    -0.08
     разм
    -0.07
    ont
    -0.07
     lavender
    -0.07
     brook
    -0.07
    POSITIVE LOGITS
     사례
    0.12
     scenarios
    0.10
    场
    0.09
    案例
    0.08
    ケース
    0.08
    Scenario
    0.08
     outweigh
    0.08
    _real
    0.08
     intra
    0.08
    _rt
    0.08
    Activations Density 0.005%

    No Known Activations