© 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. 5490
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
    ная
    -0.15
     информация
    -0.14
     metoda
    -0.14
     osoba
    -0.14
     тема
    -0.14
     база
    -0.14
    ція
    -0.14
    ительная
    -0.14
    енная
    -0.14
    тация
    -0.14
    POSITIVE LOGITS
    ующ
    0.13
     открыт
    0.11
     сам
    0.11
     втор
    0.11
    цион
    0.10
     мо
    0.09
    ич
    0.09
     кажд
    0.09
     rakenn
    0.09
    luğu
    0.09
    Activations Density 0.035%

    No Known Activations