© 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 EvalsExportsinterp-engineNEWAPI 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. 22142
    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
     verschillende
    -0.10
     verschiedener
    -0.10
     વિવિધ
    -0.09
     विभिन्न
    -0.09
     métiers
    -0.09
     verschiedene
    -0.09
     വിവിധ
    -0.09
     ವಿವಿಧ
    -0.09
     различных
    -0.09
     unterschiedliche
    -0.09
    POSITIVE LOGITS
     answer
    0.19
     your
    0.18
    answer
    0.17
    your
    0.17
    答案
    0.17
    Answer
    0.15
    _answer
    0.15
    	answer
    0.15
    回答
    0.15
    उत्तर
    0.14
    Activations Density 0.005%

    No Known Activations