© 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. 19750
    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
     corresponding
    -0.10
     associé
    -0.08
     associado
    -0.08
     correspondant
    -0.08
     correspondente
    -0.08
     colectiva
    -0.08
     coletiva
    -0.08
     correspondent
    -0.07
     collectif
    -0.07
     coletivo
    -0.07
    POSITIVE LOGITS
    Есть
    0.10
    |()↵
    0.09
     histoires
    0.09
    юць
    0.09
     tweaks
    0.08
     ёсць
    0.08
    |)↵
    0.08
     yoxdur
    0.08
     داستان
    0.08
    ្ទះ
    0.08
    Activations Density 0.000%

    No Known Activations