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. 106030
    Prev
    Next
    INDEX
    Explanations

    indexing/subscripts

    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
     ease
    -0.08
     eas
    -0.08
    歓
    -0.08
     milestones
    -0.07
    иски
    -0.07
    り
    -0.07
     цена
    -0.07
    احات
    -0.07
     handling
    -0.07
    交流
    -0.07
    POSITIVE LOGITS
    %;
    0.09
     proximal
    0.08
    .Classes
    0.08
    Arch
    0.08
     Arch
    0.08
     tempted
    0.08
    дун
    0.08
     insecure
    0.08
    spacing
    0.07
    edef
    0.07
    Activations Density 0.020%

    No Known Activations