© 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. 49075
    Prev
    Next
    INDEX
    Explanations

    Romanian language

    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
     культура
    -0.11
     новая
    -0.10
     ваша
    -0.10
     Ελλάδα
    -0.10
     kultura
    -0.09
     voda
    -0.09
     содержание
    -0.09
     nový
    -0.09
    альная
    -0.09
    ులు
    -0.09
    POSITIVE LOGITS
     unui
    0.25
     unei
    0.24
     lui
    0.18
     celor
    0.17
     kët
    0.17
     celui
    0.15
     aceste
    0.14
     unor
    0.13
     revenir
    0.13
     durer
    0.13
    Activations Density 0.002%

    No Known Activations