© 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. 44328
    Prev
    Next
    INDEX
    Explanations

    bundling

    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
     undefined
    -0.09
     mx
    -0.08
     rating
    -0.08
     established
    -0.07
     yielded
    -0.07
    (mx
    -0.07
     experimentar
    -0.07
     Rating
    -0.07
     influenced
    -0.07
    (te
    -0.07
    POSITIVE LOGITS
    embedding
    0.11
     embed
    0.11
     embedding
    0.11
    Embedding
    0.10
     Embed
    0.09
     embeds
    0.09
    _embed
    0.09
    Embed
    0.09
    embed
    0.09
     Everything
    0.09
    Activations Density 0.010%

    No Known Activations