© 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. 23-RESID-POST-AA
    11. 5696
    Prev
    Next
    INDEX
    Explanations

    ent

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Evid
    -0.08
     ঘ
    -0.07
     сек
    -0.07
     berubah
    -0.07
     Imp
    -0.07
    ೀ
    -0.07
     dee
    -0.07
    ேய
    -0.07
     configurable
    -0.07
     Dee
    -0.07
    POSITIVE LOGITS
    .Cursor
    0.09
    ’intervention
    0.09
    Cursor
    0.08
    DB
    0.08
     nominations
    0.08
    URRENC
    0.08
    odium
    0.08
    .Employee
    0.08
    db
    0.08
    oulder
    0.08
    Activations Density 0.000%

    No Known Activations