© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96960
    Prev
    Next
    INDEX
    Explanations

    water

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    领域
    -0.09
     sticker
    -0.08
    gebied
    -0.08
     stickers
    -0.08
    itoy
    -0.08
    ateau
    -0.08
     thêm
    -0.08
    FIELD
    -0.08
     Rockstar
    -0.08
    DOMAIN
    -0.07
    POSITIVE LOGITS
    -driven
    0.14
    -powered
    0.12
    power
    0.12
     शक्ति
    0.12
     power
    0.11
    _power
    0.11
     drove
    0.11
    _POWER
    0.11
    -power
    0.11
    Driven
    0.10
    Activations Density 0.006%

    No Known Activations