© 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. 21620
    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
     egiten
    -0.08
     delight
    -0.08
     perusahaan
    -0.08
     établissement
    -0.08
     portable
    -0.07
    anzvi
    -0.07
    和值
    -0.07
    兼职
    -0.07
     wearable
    -0.07
    ейтін
    -0.07
    POSITIVE LOGITS
     الأزمة
    0.15
     scandals
    0.15
     أزمة
    0.14
     aftermath
    0.14
     protests
    0.14
     사건
    0.14
     ocorrido
    0.14
     జరిగిన
    0.13
     Ereign
    0.13
     infamous
    0.13
    Activations Density 0.228%

    No Known Activations