© 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. 54422
    Prev
    Next
    INDEX
    Explanations

    Formatting specifications and instructions

    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
     трав
    -0.09
     hikes
    -0.08
     assault
    -0.08
     walks
    -0.08
     surprising
    -0.08
     assaults
    -0.08
     beraten
    -0.07
     arsenal
    -0.07
     profiler
    -0.07
     fibras
    -0.07
    POSITIVE LOGITS
     punctuation
    0.10
     format
    0.10
     formatting
    0.09
    	format
    0.09
    格式
    0.09
    统一
    0.09
    format
    0.09
     kawai
    0.08
     comma
    0.08
     resembles
    0.08
    Activations Density 0.019%

    No Known Activations