© 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. 68810
    Prev
    Next
    INDEX
    Explanations

    Similes

    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
     sve
    -0.10
    GLE
    -0.08
    .ve
    -0.08
    rista
    -0.07
     Nug
    -0.07
    _fig
    -0.07
    FE
    -0.07
     ад
    -0.07
     isempty
    -0.07
     Saw
    -0.07
    POSITIVE LOGITS
    afr
    0.08
     Morg
    0.08
     onların
    0.08
    electronics
    0.08
    paramos
    0.07
    -paying
    0.07
    -touch
    0.07
     onları
    0.07
     BTS
    0.07
    chmod
    0.07
    Activations Density 0.004%

    No Known Activations