© 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. 96388
    Prev
    Next
    INDEX
    Explanations

    ty

    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
     πολλά
    -0.12
     пользов
    -0.11
     produkty
    -0.10
     beteg
    -0.10
     інш
    -0.10
     клиент
    -0.10
     artworks
    -0.10
     invoices
    -0.10
     покуп
    -0.09
     sayings
    -0.09
    POSITIVE LOGITS
     жителей
    0.16
     людей
    0.15
     участников
    0.14
     работников
    0.13
     представителей
    0.13
     жиль
    0.13
     директ
    0.13
     населения
    0.13
     сотрудников
    0.13
     детей
    0.12
    Activations Density 0.026%

    No Known Activations