© 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. 129107
    Prev
    Next
    INDEX
    Explanations

    take-out food

    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
    .gl
    -0.08
    Vit
    -0.08
     Führung
    -0.08
    گاهی
    -0.08
    fil
    -0.07
    ada
    -0.07
     asistentes
    -0.07
    jör
    -0.07
    bi
    -0.07
     സ
    -0.07
    POSITIVE LOGITS
     restaurant
    0.09
     Pizza
    0.09
     pizza
    0.09
    配送
    0.09
     spam
    0.08
     prison
    0.08
     distributor
    0.08
     leverancier
    0.08
     monster
    0.08
    宅
    0.08
    Activations Density 0.046%

    No Known Activations