© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47674
    Prev
    Next
    INDEX
    Explanations

    say "json"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GTK
    -0.10
    (XML
    -0.10
    	URL
    -0.10
     URI
    -0.09
     XML
    -0.09
     IRQ
    -0.09
     HTML
    -0.09
    HTML
    -0.09
     SVG
    -0.09
    XML
    -0.09
    POSITIVE LOGITS
     json
    0.28
    (json
    0.26
    json
    0.23
    	json
    0.23
    =json
    0.21
    ,json
    0.19
     csv
    0.16
    .json
    0.16
     yaml
    0.15
     sql
    0.15
    Activations Density 0.011%

    No Known Activations