© 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. 22709
    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
     precisely
    -0.10
     제공합니다
    -0.09
     точно
    -0.09
     vrlo
    -0.09
     "','"
    -0.08
     precies
    -0.08
     zeer
    -0.08
     exakt
    -0.08
     쉽게
    -0.08
     kannattaa
    -0.08
    POSITIVE LOGITS
     sedang
    0.11
    ’s
    0.11
    正在
    0.11
     sparked
    0.11
     đang
    0.11
     adventures
    0.10
     estás
    0.09
     stirred
    0.09
    ’S
    0.09
     Adventures
    0.09
    Activations Density 0.007%

    No Known Activations