© 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. 19-RESID-POST-AA
    11. 102589
    Prev
    Next
    INDEX
    Explanations

    say "base"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jessica
    -0.10
     Gerry
    -0.10
    jsonwebtoken
    -0.10
    transactions
    -0.10
    jwt
    -0.10
     politician
    -0.10
     Jerry
    -0.10
     journalist
    -0.10
     jane
    -0.10
    _transaction
    -0.10
    POSITIVE LOGITS
     base
    0.20
    .base
    0.18
    _base
    0.18
    	base
    0.18
     baze
    0.17
    _BASE
    0.17
     базы
    0.17
     बेस
    0.16
    基地
    0.16
    Base
    0.16
    Activations Density 0.063%

    No Known Activations