Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44179
    Prev
    Next
    INDEX
    Explanations

    ups

    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
    jenige
    -0.09
    lığı
    -0.08
    hlelo
    -0.08
    asyonu
    -0.08
    itego
    -0.08
     pion
    -0.07
    headed
    -0.07
    ;)↵↵
    -0.07
    yndham
    -0.07
    ments
    -0.07
    POSITIVE LOGITS
     balcony
    0.08
     eut
    0.08
     чинов
    0.08
    bour
    0.07
     tẹlẹ
    0.07
     та
    0.07
     السود
    0.07
     agb
    0.07
    Ep
    0.07
     balconies
    0.07
    Activations Density 0.003%

    No Known Activations