© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 31339
    Prev
    Next
    INDEX
    Explanations

    line segments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Genes
    -0.08
    理论
    -0.08
     cultures
    -0.08
     coveted
    -0.07
    oler
    -0.07
     MY
    -0.07
     spores
    -0.07
    Viewed
    -0.07
     toplum
    -0.07
     cookies
    -0.07
    POSITIVE LOGITS
    Segment
    0.12
     abrupt
    0.12
    Slope
    0.12
    Polyline
    0.11
    _segment
    0.11
     segments
    0.11
    Bezier
    0.11
     segment
    0.11
    Segments
    0.11
    Spline
    0.11
    Activations Density 0.022%

    No Known Activations