© 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. 20176
    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
     the
    -0.08
     `/
    -0.08
    idän
    -0.08
    arschijnlijk
    -0.08
    @Transactional
    -0.08
    ांकि
    -0.08
    һ
    -0.08
    Пол
    -0.08
     அதை
    -0.07
     Пол
    -0.07
    POSITIVE LOGITS
     avec
    0.09
     şekl
    0.08
     或
    0.08
    Avec
    0.08
     Avec
    0.08
     >",
    0.08
     với
    0.08
    نز
    0.08
    ులతో
    0.08
     형태
    0.08
    Activations Density 0.010%

    No Known Activations