© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 109947
    Prev
    Next
    INDEX
    Explanations

    Describing figures

    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
    Negative Logits
     codecs
    -0.09
     osu
    -0.08
     emojis
    -0.08
    sé
    -0.08
     assertion
    -0.08
    跨
    -0.08
     Martini
    -0.08
     cocktails
    -0.07
     codec
    -0.07
    .stdout
    -0.07
    POSITIVE LOGITS
    Figure
    0.11
     depicted
    0.10
    Figures
    0.10
     pictured
    0.09
     Figure
    0.09
     protr
    0.09
     (§
    0.09
     worn
    0.09
     Figures
    0.08
    Diagram
    0.08
    Activations Density 0.004%

    No Known Activations