© 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. 25124
    Prev
    Next
    INDEX
    Explanations

    Thai language

    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
    (Properties
    -0.09
     Dispatcher
    -0.08
     unconditional
    -0.08
     связи
    -0.08
     Централь
    -0.08
     Edition
    -0.08
    ophile
    -0.08
    .properties
    -0.08
     Assembleia
    -0.08
    Ы
    -0.08
    POSITIVE LOGITS
     Thai
    0.10
    台湾
    0.10
    าม
    0.10
     Taipei
    0.09
     Thailand
    0.09
    กับ
    0.09
     Taiwan
    0.09
     ตัว
    0.09
    ตัว
    0.09
    มาก
    0.09
    Activations Density 0.026%

    No Known Activations