© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20566
    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
     gunakan
    -0.09
     koristiti
    -0.08
     posiada
    -0.08
     використов
    -0.08
     izmant
    -0.08
     gebruiken
    -0.08
     использовать
    -0.08
     يستخدم
    -0.08
    ್ಧ
    -0.08
     använda
    -0.08
    POSITIVE LOGITS
     itself
    0.10
    ly
    0.10
     differently
    0.09
    elijkheden
    0.09
    ing
    0.09
     собой
    0.09
     physically
    0.08
    ational
    0.08
     concret
    0.08
     concr
    0.08
    Activations Density 0.005%

    No Known Activations