© 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. 19515
    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
    ίνει
    -0.07
    etted
    -0.07
     memb
    -0.07
    nicy
    -0.07
     થયો
    -0.07
    light
    -0.07
    -0.06
     μεγά
    -0.06
    	G
    -0.06
     Examiner
    -0.06
    POSITIVE LOGITS
    :x
    0.18
    :flutter
    0.18
    :\
    0.18
    :file
    0.18
    :item
    0.18
    :get
    0.18
    :type
    0.17
    :[
    0.17
    :user
    0.17
    :
    0.17
    Activations Density 0.061%
    No Known Activations