© 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. 22034
    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
    ishments
    -0.09
    abend
    -0.09
    the
    -0.09
    some
    -0.09
    actics
    -0.09
    aryna
    -0.08
    ah
    -0.08
    those
    -0.08
    adau
    -0.08
    ad
    -0.08
    POSITIVE LOGITS
     relation
    0.09
    ாள்
    0.09
    (of
    0.09
     alimentaire
    0.08
     relations
    0.08
    Relation
    0.08
    ציה
    0.08
    ity
    0.08
    _relation
    0.08
     نیاز
    0.08
    Activations Density 0.008%

    No Known Activations