© 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. 20034
    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
     resulted
    -0.08
     वृद्धि
    -0.08
    増
    -0.08
     увеличение
    -0.08
     resulting
    -0.08
     كت
    -0.08
     увелич
    -0.08
    ಿಧ
    -0.08
    છી
    -0.08
    ăt
    -0.08
    POSITIVE LOGITS
     nuance
    0.20
     nuances
    0.20
     nuanced
    0.17
     subtle
    0.16
     tricky
    0.14
     intric
    0.12
     disclaim
    0.12
     interpretations
    0.12
     ню
    0.12
     borderline
    0.11
    Activations Density 0.043%

    No Known Activations