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. 58341
    Prev
    Next
    INDEX
    Explanations

    drinking water

    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
    版本
    -0.08
    resent
    -0.08
     vd
    -0.07
     Has
    -0.07
     Bridges
    -0.07
     analyze
    -0.07
    风险
    -0.07
     explosion
    -0.07
     Proven
    -0.07
    vd
    -0.07
    POSITIVE LOGITS
     restroom
    0.12
     воспользоваться
    0.11
    澡
    0.10
     erled
    0.10
    自慰
    0.10
     заниматься
    0.10
     descansar
    0.10
     suor
    0.10
     आराम
    0.10
     bathroom
    0.10
    Activations Density 0.118%

    No Known Activations