© 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. 68442
    Prev
    Next
    INDEX
    Explanations

    product codes and specifications

    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
    arsu
    -0.08
     voraus
    -0.08
     իրավ
    -0.08
    風吹けば
    -0.08
     სამართ
    -0.08
    骰
    -0.08
    ાહેર
    -0.08
     emploi
    -0.08
     beý
    -0.08
     tshuab
    -0.08
    POSITIVE LOGITS
     variants
    0.14
     versions
    0.13
     versões
    0.13
     variant
    0.13
     versiones
    0.13
     version
    0.13
     версия
    0.12
    版本
    0.12
     संस्करण
    0.12
     نسخه
    0.12
    Activations Density 0.079%

    No Known Activations