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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12153
    Prev
    Next
    INDEX
    Explanations

    powers

    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
     Schwarz
    -0.08
     Pearson
    -0.08
     bonnet
    -0.07
    Executable
    -0.07
     Ej
    -0.07
     bev
    -0.07
    instr
    -0.07
     movers
    -0.07
     затрат
    -0.07
    _ie
    -0.07
    POSITIVE LOGITS
    Cole
    0.08
    体系
    0.08
    lichkeiten
    0.08
     Nadia
    0.08
    栏
    0.07
     substances
    0.07
    览
    0.07
     médical
    0.07
     اعمال
    0.07
    ங்களை
    0.07
    Activations Density 0.012%

    No Known Activations