© 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 EvalsExportsAPI 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. 19827
    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
     to
    -0.10
    ,
    -0.09
     I'll
    -0.08
     desired
    -0.08
     more
    -0.08
    To
    -0.08
    desired
    -0.08
     my
    -0.08
     for
    -0.08
    POSITIVE LOGITS
     יודע
    0.16
     know
    0.16
    知道
    0.16
     wusste
    0.15
     जानते
    0.15
     יודעים
    0.14
     knew
    0.14
     sabia
    0.14
    know
    0.14
     يعرف
    0.14
    Activations Density 0.002%

    No Known Activations