© 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. 23-RESID-POST-AA
    11. 49218
    Prev
    Next
    INDEX
    Explanations

    揭

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    овать
    -0.09
    ствовать
    -0.08
     clerk
    -0.08
    עמ
    -0.08
    pector
    -0.07
    ating
    -0.07
    하며
    -0.07
    ует
    -0.07
    уя
    -0.07
     coloration
    -0.07
    POSITIVE LOGITS
    示
    0.20
    开
    0.16
    露
    0.15
    开的
    0.15
    开什么
    0.14
    开心
    0.14
    開
    0.14
    晓
    0.14
    开彩
    0.14
     示
    0.13
    Activations Density 0.002%

    No Known Activations