© 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. 15-RESID-POST-AA
    11. 16612
    Prev
    Next
    INDEX
    Explanations

    say "years"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     violating
    -0.08
     violate
    -0.08
     rejects
    -0.08
     رسمی
    -0.08
     disagree
    -0.08
     violates
    -0.08
    .css
    -0.08
    .Sample
    -0.08
    ivas
    -0.08
    .reject
    -0.07
    POSITIVE LOGITS
    整数
    0.11
     numeral
    0.10
     figur
    0.10
    年份
    0.09
     число
    0.09
    _Integer
    0.09
     संख्या
    0.09
     अंक
    0.09
     digits
    0.09
     nọmba
    0.09
    Activations Density 0.022%

    No Known Activations