© 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. 19915
    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
    aturity
    -0.08
     almond
    -0.08
     pancakes
    -0.08
    Promise
    -0.07
     prosecut
    -0.07
     pard
    -0.07
     wisdom
    -0.07
     promises
    -0.07
    =").
    -0.07
     shrub
    -0.07
    POSITIVE LOGITS
     Designers
    0.17
     designers
    0.16
     디자인
    0.16
    设计
    0.15
     худож
    0.15
     Diseño
    0.15
     дизайнер
    0.15
     طراحی
    0.15
     डिजाइन
    0.14
     diseñador
    0.14
    Activations Density 0.041%

    No Known Activations