© 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. 77993
    Prev
    Next
    INDEX
    Explanations

    sum

    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
    ULAR
    -0.09
    lines
    -0.08
    ual
    -0.07
     Technologie
    -0.07
     อย่าง
    -0.07
     hallmark
    -0.07
     carpeta
    -0.07
    ifiers
    -0.07
    imed
    -0.07
     technology
    -0.07
    POSITIVE LOGITS
    	Collections
    0.08
     حاصل
    0.08
     राशि
    0.08
    	Collection
    0.08
     Tung
    0.08
     Sai
    0.08
    Largest
    0.08
    .rece
    0.07
     owed
    0.07
     Sum
    0.07
    Activations Density 0.018%

    No Known Activations