© 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. 22627
    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
     is
    -0.11
     является
    -0.11
     isaa
    -0.10
     என்பது
    -0.10
     использ
    -0.09
     was
    -0.09
     from
    -0.09
     vara
    -0.09
     être
    -0.09
     varit
    -0.09
    POSITIVE LOGITS
    \n
    0.16
    ヽ
    0.10
    　三
    0.10
    　在
    0.10
    يمكن
    0.10
    �
    0.10
    တွေ
    0.10
    

    0.10
    Dalam
    0.09
    0.09
    Activations Density 0.002%
    No Known Activations