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. 77363
    Prev
    Next
    INDEX
    Explanations

    Straight-line depreciation

    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
     quieter
    -0.09
    acific
    -0.08
    .commands
    -0.08
    _connect
    -0.08
    .coordinate
    -0.08
    .message
    -0.07
    -0.07
    -debug
    -0.07
     stranger
    -0.07
     communicate
    -0.07
    POSITIVE LOGITS
     срока
    0.11
     срок
    0.10
     기간
    0.10
    期限
    0.09
     сроки
    0.09
     depreciation
    0.09
    年度
    0.09
     annuelle
    0.08
     רוח
    0.08
    合理
    0.08
    Activations Density 0.004%

    No Known Activations