© 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. 21210
    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
     rectangle
    -0.08
    .extract
    -0.08
     dimension
    -0.08
     struttura
    -0.07
     الهي
    -0.07
     externe
    -0.07
     supprimer
    -0.07
    неш
    -0.07
     structures
    -0.07
     extracting
    -0.07
    POSITIVE LOGITS
     reconstruction
    0.09
     preservation
    0.09
     автоб
    0.09
    ynthesis
    0.09
     рекон
    0.08
     renovación
    0.08
    automaten
    0.08
    otud
    0.08
    птом
    0.08
     Preservation
    0.08
    Activations Density 0.001%

    No Known Activations