© 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. 103396
    Prev
    Next
    INDEX
    Explanations

    empty

    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
    рут
    -0.08
    íncipe
    -0.08
     einzelnen
    -0.08
    /mobile
    -0.08
    édie
    -0.08
    seille
    -0.08
    ärk
    -0.08
     greasy
    -0.07
     nieuwsbrief
    -0.07
    ẩ
    -0.07
    POSITIVE LOGITS
     пуст
    0.19
     boş
    0.18
     empt
    0.18
     absence
    0.17
     empty
    0.16
     vazio
    0.16
     kosong
    0.16
     ausência
    0.16
     vacío
    0.16
    Empty
    0.16
    Activations Density 0.023%

    No Known Activations