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. 102820
    Prev
    Next
    INDEX
    Explanations

    file paths and dates

    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
     disputes
    -0.08
    oma
    -0.07
    vec
    -0.07
    holds
    -0.07
     exert
    -0.07
     pathways
    -0.07
     bid
    -0.07
     ejercer
    -0.07
    omas
    -0.07
     callbacks
    -0.07
    POSITIVE LOGITS
     날짜
    0.13
     timestamp
    0.13
     日期
    0.13
     తేద
    0.12
     તારીખ
    0.12
     தேதி
    0.12
    当天
    0.12
     今日
    0.11
    (date
    0.11
     naming
    0.11
    Activations Density 0.009%

    No Known Activations