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. 109679
    Prev
    Next
    INDEX
    Explanations

    multiple languages/writing

    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
    账号
    -0.09
    ORD
    -0.08
    ordo
    -0.08
    kové
    -0.08
     cheer
    -0.08
     Vincent
    -0.08
     Ord
    -0.08
     Ranger
    -0.08
     Pencil
    -0.07
    ódigo
    -0.07
    POSITIVE LOGITS
    Strategies
    0.09
    》中
    0.08
    Patterns
    0.08
    Нед
    0.08
     ಕುರಿತು
    0.08
    ">(
    0.08
    Effects
    0.08
    ...,
    0.07
    DAOImpl
    0.07
    专题
    0.07
    Activations Density 0.197%

    No Known Activations