© 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. 21347
    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
     analyzing
    -0.10
     monitored
    -0.09
     measurable
    -0.09
     analyzed
    -0.09
     untersucht
    -0.09
     investigated
    -0.09
     analyze
    -0.09
     бақыла
    -0.09
     analisar
    -0.08
     analizar
    -0.08
    POSITIVE LOGITS
     Jika
    0.17
     If
    0.16
     nếu
    0.16
     فإذا
    0.16
     Nếu
    0.16
     jika
    0.16
    Jika
    0.16
     ако
    0.16
    If
    0.15
    Nếu
    0.15
    Activations Density 0.076%

    No Known Activations