© 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. 19562
    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
     eventualmente
    -0.08
     eventueel
    -0.07
    Ultimately
    -0.07
     cascading
    -0.07
    [:,
    -0.07
    épe
    -0.07
     insiste
    -0.07
     ampli
    -0.06
     acompañ
    -0.06
    As
    -0.06
    POSITIVE LOGITS
     hiatus
    0.21
     منذ
    0.19
     hasn't
    0.18
     haven't
    0.17
     hadn't
    0.17
     久
    0.16
     dormant
    0.16
     છેલ્લા
    0.16
     давно
    0.16
     sinds
    0.16
    Activations Density 0.066%

    No Known Activations