© 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. 19215
    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
    -two
    -0.09
    ,\
    -0.08
    Two
    -0.08
     then
    -0.08
     two
    -0.08
    lies
    -0.07
    -called
    -0.07
    -ad
    -0.07
    two
    -0.07
    	then
    -0.07
    POSITIVE LOGITS
     Breakdown
    0.10
     Breaking
    0.10
     Count
    0.10
     sorgfält
    0.10
     Enumer
    0.10
     Enumeration
    0.09
     vowels
    0.09
     Let's
    0.09
    ：
    0.09
     Carefully
    0.09
    Activations Density 0.005%

    No Known Activations