© 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. 19-RESID-POST-AA
    11. 103591
    Prev
    Next
    INDEX
    Explanations

    Programming/technical articles in Russian

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oporosis
    -0.29
    adecimal
    -0.24
    acency
    -0.22
    bardziej
    -0.21
    ariance
    -0.20
    gunaan
    -0.20
    bụ
    -0.20
    umatoid
    -0.19
    ellaneous
    -0.19
    etheless
    -0.19
    POSITIVE LOGITS
    рабаты
    0.10
    فرادی
    0.10
    افع
    0.10
    ыск
    0.09
    ันท
    0.09
    ���
    0.09
    ыми
    0.09
    ํา
    0.08
    уды
    0.08
    ‌ల
    0.08
    Activations Density 0.156%

    No Known Activations