© 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. 108445
    Prev
    Next
    INDEX
    Explanations

    Database identifiers

    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
    .pause
    -0.08
     neglected
    -0.08
     médit
    -0.07
     marinade
    -0.07
    "Oh
    -0.07
     trän
    -0.07
     PURE
    -0.07
    "And
    -0.07
    Paused
    -0.07
     distributions
    -0.07
    POSITIVE LOGITS
    _ID
    0.10
     GUID
    0.09
    _gid
    0.09
    Id
    0.08
     രാജ
    0.08
    GUID
    0.08
    (cid
    0.08
    (fid
    0.08
    ооп
    0.08
    obi
    0.08
    Activations Density 0.009%

    No Known Activations