© 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. 21008
    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
     exclaimed
    -0.09
     hash
    -0.08
    Mux
    -0.08
    ynom
    -0.08
    Votes
    -0.08
     hashmap
    -0.08
    lüsse
    -0.08
    _hash
    -0.08
     चिन
    -0.08
     ciphertext
    -0.08
    POSITIVE LOGITS
    培训
    0.50
     training
    0.46
     प्रशिक्षण
    0.45
     പരിശീല
    0.42
     trainingen
    0.42
     التدريب
    0.41
     Training
    0.41
     treinamento
    0.41
    Training
    0.41
     તાલ
    0.40
    Activations Density 0.175%

    No Known Activations