© 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. 68641
    Prev
    Next
    INDEX
    Explanations

    currency and trade

    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
    _mutex
    -0.08
     《
    -0.08
    agram
    -0.08
    _PS
    -0.07
     מיל
    -0.07
     Gardens
    -0.07
     измер
    -0.07
     Mach
    -0.07
     Σε
    -0.07
     Partners
    -0.07
    POSITIVE LOGITS
     tough
    0.09
     tougher
    0.08
     තම
    0.08
    .www
    0.08
     beneficial
    0.08
    vand
    0.08
     électron
    0.08
    가격
    0.08
     سخت
    0.08
     meningkatkan
    0.08
    Activations Density 0.006%

    No Known Activations