© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 20525
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     becoming
    -0.09
    .“↵
    -0.09
    又黄
    -0.09
     xub
    -0.09
     crucial
    -0.09
    =",
    -0.08
    凤凰大
    -0.08
    大发展
    -0.08
     niyang
    -0.08
     description
    -0.08
    POSITIVE LOGITS
    {}{
    0.11
     использовать
    0.10
    {}{↵
    0.10
     ઉપયોગ
    0.09
     பயன்படுத்த
    0.09
    useid
    0.09
    frac
    0.09
    vänd
    0.09
     사용
    0.09
     использовании
    0.09
    Activations Density 0.011%

    No Known Activations