© 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. 20989
    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
     here's
    -0.08
    /or
    -0.08
     acceptable
    -0.08
     correcto
    -0.07
     beoordeling
    -0.07
     Einrichtungen
    -0.07
     posiblemente
    -0.07
     صحي
    -0.07
     محطم
    -0.07
     procedimentos
    -0.07
    POSITIVE LOGITS
    Narr
    0.13
     narratives
    0.13
     narrative
    0.12
     narrativa
    0.11
     कथा
    0.11
    argument
    0.10
     storytelling
    0.10
    Argument
    0.10
     urge
    0.10
    /read
    0.10
    Activations Density 0.007%

    No Known Activations