© 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. 15-RESID-POST-AA
    11. 16411
    Prev
    Next
    INDEX
    Explanations

    Realistic details

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
     आयोजित
    -0.08
     afo
    -0.08
    .navigate
    -0.08
     voorlop
    -0.08
    結果
    -0.08
     waliin
    -0.07
     advisory
    -0.07
    .insert
    -0.07
     supplementation
    -0.07
    POSITIVE LOGITS
    细
    0.17
     تفاصيل
    0.16
     nuances
    0.15
    細
    0.15
     detaill
    0.15
    Detailed
    0.14
     വിശദ
    0.14
     детали
    0.14
     বিস্তারিত
    0.14
     déta
    0.14
    Activations Density 0.022%
    No Known Activations