© 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. 7-RESID-POST-AA
    11. 1207
    Prev
    Next
    INDEX
    Explanations

    Soviet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SEN
    -0.08
     Waiting
    -0.08
    调用
    -0.08
     Veri
    -0.08
    /usr
    -0.08
     obe
    -0.07
    DCALL
    -0.07
    什么
    -0.07
     આય
    -0.07
    Waiting
    -0.07
    POSITIVE LOGITS
    -era
    0.14
    geschichte
    0.11
     historique
    0.10
    history
    0.10
    (history
    0.10
     ചരിത്ര
    0.10
    歷
    0.09
     прошлого
    0.09
     historical
    0.09
     history
    0.09
    Activations Density 0.031%

    No Known Activations