© 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. 20891
    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
     verilen
    -0.10
     peut
    -0.09
    तो
    -0.09
     veut
    -0.08
     waarom
    -0.08
    ness
    -0.08
     može
    -0.08
     peux
    -0.08
     cómo
    -0.08
     hoe
    -0.08
    POSITIVE LOGITS
     envision
    0.12
    ’re
    0.12
    _HAVE
    0.11
     ذهن
    0.10
     gedachten
    0.10
     نیاز
    0.10
     thoughts
    0.10
    正在
    0.10
     imagining
    0.09
     تحتاج
    0.09
    Activations Density 0.007%

    No Known Activations