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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26136
    Prev
    Next
    INDEX
    Explanations

    purification and separation

    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
    Mood
    -0.09
     fearless
    -0.09
     SHALL
    -0.09
     courageous
    -0.08
     courage
    -0.08
     cellspacing
    -0.08
    Marked
    -0.08
    充
    -0.08
    CELL
    -0.08
    Feeling
    -0.08
    POSITIVE LOGITS
     wastewater
    0.10
     recycling
    0.10
     purification
    0.09
     afval
    0.09
     profit
    0.09
     shampoo
    0.09
     промышлен
    0.09
    .cleanup
    0.09
     beneficiation
    0.09
     recycle
    0.09
    Activations Density 0.005%

    No Known Activations