© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18498
    Prev
    Next
    INDEX
    Explanations

    say "="

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _uart
    -0.10
    _grp
    -0.10
    _UART
    -0.10
    _resp
    -0.09
    ?).
    -0.09
    _swap
    -0.09
    _日本
    -0.09
    ()?
    -0.09
    уулах
    -0.09
    _uri
    -0.09
    POSITIVE LOGITS
    Now
    0.12
    For
    0.10
    Use
    0.10
    From
    0.10
    That
    0.10
    Using
    0.09
    “That
    0.09
     Now
    0.09
    How
    0.09
     =↵
    0.09
    Activations Density 0.009%

    No Known Activations