© 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. 102339
    Prev
    Next
    INDEX
    Explanations

    Ops

    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
    ism
    -0.08
    ismes
    -0.08
     им
    -0.07
     точно
    -0.07
     specifiek
    -0.07
     предлага
    -0.07
     формы
    -0.07
    isme
    -0.07
     şi
    -0.07
     précisément
    -0.07
    POSITIVE LOGITS
    रेशन
    0.14
    acje
    0.12
    ational
    0.12
    ేషన్
    0.12
    ేష
    0.11
    aciones
    0.11
    ACIONES
    0.11
    asjoner
    0.11
    ATIONS
    0.11
    acional
    0.11
    Activations Density 0.013%

    No Known Activations