© 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. 20067
    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
     CEO
    -0.10
     nicer
    -0.09
     meetup
    -0.09
     सोमवार
    -0.09
     ✅
    -0.09
     phishing
    -0.09
     každý
    -0.09
    每天
    -0.09
     scheduler
    -0.09
     internship
    -0.09
    POSITIVE LOGITS
     juxtap
    0.14
     evoc
    0.13
     sensual
    0.13
     reminiscent
    0.13
     motifs
    0.13
     словно
    0.12
     depicting
    0.12
     grotes
    0.12
     изображ
    0.12
     imagery
    0.12
    Activations Density 0.040%

    No Known Activations