© 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. 3-RESID-POST-AA
    11. 13122
    Prev
    Next
    INDEX
    Explanations

    core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dad
    -0.09
    wert
    -0.08
     garner
    -0.08
     apparel
    -0.08
    ılar
    -0.08
     affluent
    -0.07
     HAS
    -0.07
     merchandising
    -0.07
     underv
    -0.07
    个人
    -0.07
    POSITIVE LOGITS
     Sper
    0.07
    _TYP
    0.07
     Facult
    0.07
     Fahrt
    0.07
     Boh
    0.07
     infl
    0.07
     تك
    0.07
    ಾದ
    0.07
    ડ
    0.07
     Silent
    0.07
    Activations Density 0.008%

    No Known Activations