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. 112581
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    ızı
    -0.09
    опат
    -0.08
    	option
    -0.08
    'use
    -0.08
    �
    -0.08
    volatile
    -0.08
    _JS
    -0.08
     Iterator
    -0.07
     Bounding
    -0.07
     Heads
    -0.07
    POSITIVE LOGITS
    ->{
    0.07
     waxay
    0.07
     Sized
    0.07
     parted
    0.07
     bible
    0.07
    ai
    0.07
     repos
    0.07
     ci
    0.07
     cyst
    0.07
     bå
    0.07
    Activations Density 0.069%

    No Known Activations