© 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. 77970
    Prev
    Next
    INDEX
    Explanations

    Thailand

    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
     Skyline
    -0.08
     Vent
    -0.08
     Terry
    -0.08
     нарушения
    -0.08
    vação
    -0.08
     Estates
    -0.08
     DIV
    -0.08
     STEM
    -0.07
     UNC
    -0.07
     Lisp
    -0.07
    POSITIVE LOGITS
     Thailand
    0.15
     Thai
    0.15
     Bangkok
    0.13
    Thailand
    0.12
    Thai
    0.12
     thailand
    0.11
     Malaysia
    0.11
     Myanmar
    0.10
     ASEAN
    0.10
     Cambodia
    0.10
    Activations Density 0.020%

    No Known Activations