© 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. 95831
    Prev
    Next
    INDEX
    Explanations

    对

    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
     эта
    -0.09
     �
    -0.09
     gesetzt
    -0.09
     Basa
    -0.08
     setzte
    -0.08
     setzt
    -0.08
    -ca
    -0.08
    pered
    -0.08
    忍
    -0.08
     ironically
    -0.08
    POSITIVE LOGITS
    抗
    0.10
    不起
    0.10
    照
    0.08
     unborn
    0.07
    Traveler
    0.07
    广大
    0.07
     Resistance
    0.07
    ign
    0.07
    尚
    0.07
    齐
    0.07
    Activations Density 0.011%

    No Known Activations