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. 90126
    Prev
    Next
    INDEX
    Explanations

    hemp

    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
     السين
    -0.09
    _department
    -0.08
     kontro
    -0.08
     ताप
    -0.08
    .Command
    -0.08
    Department
    -0.08
    	create
    -0.08
     departments
    -0.08
    _CREAT
    -0.08
     teatr
    -0.08
    POSITIVE LOGITS
     powders
    0.11
    flakes
    0.10
     Hoodie
    0.10
     graines
    0.10
     chia
    0.10
     oats
    0.09
     powdered
    0.09
     coins
    0.09
    粉
    0.09
    weight
    0.09
    Activations Density 0.013%

    No Known Activations