© 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. 23-RESID-POST-AA
    11. 96327
    Prev
    Next
    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mlx
    -0.08
     ppl
    -0.08
    ayd
    -0.08
     mse
    -0.07
     noy
    -0.07
     genoemd
    -0.07
     aad
    -0.07
     Huntington
    -0.07
     incid
    -0.07
    endido
    -0.07
    POSITIVE LOGITS
    ZIP
    0.15
    zip
    0.14
    Zip
    0.11
     zip
    0.10
     zipper
    0.10
     unzip
    0.09
    _zip
    0.09
    z
    0.09
     ZIP
    0.09
     zipped
    0.09
    Activations Density 0.001%

    No Known Activations