© 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. 103550
    Prev
    Next
    INDEX
    Explanations

    /

    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
     haddii
    -0.10
     essere
    -0.09
     nove
    -0.09
     espan
    -0.09
     wenn
    -0.09
     idan
    -0.09
     if
    -0.09
     малень
    -0.09
     ragaz
    -0.09
     якщо
    -0.09
    POSITIVE LOGITS
    /components
    0.10
    ۲۰۱
    0.10
    ./
    0.10
    /_
    0.10
    /material
    0.09
    /...
    0.09
    �
    0.09
    ðar
    0.09
    ụkụ
    0.09
    /sys
    0.09
    Activations Density 0.004%

    No Known Activations