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. 78519
    Prev
    Next
    INDEX
    Explanations

    Python code

    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
    iyyət
    -0.09
     стоимость
    -0.09
     상승
    -0.09
     стоимости
    -0.08
    height
    -0.08
     बिजली
    -0.08
    нах
    -0.08
     цену
    -0.08
    	height
    -0.08
     tractors
    -0.08
    POSITIVE LOGITS
     empty
    0.15
    (empty
    0.13
    -empty
    0.13
     vazio
    0.12
    empty
    0.12
    .empty
    0.12
     Empty
    0.12
    _empty
    0.12
    Empty
    0.12
     пуст
    0.11
    Activations Density 0.009%

    No Known Activations