© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102143
    Prev
    Next
    INDEX
    Explanations

    --

    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
    (Employee
    -0.10
    (VAR
    -0.09
    -Core
    -0.09
    "А
    -0.09
    (each
    -0.09
     ​
    -0.09
    ♫
    -0.09
    (Properties
    -0.08
    (Student
    -0.08
    <Employee
    -0.08
    POSITIVE LOGITS
    ு
    0.11
     vs
    0.10
    .
    0.10
    ,
    0.10
    ు
    0.09
    s
    0.09
    u
    0.09
    )
    0.09
    draft
    0.09
    .↵↵
    0.09
    Activations Density 0.001%

    No Known Activations