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. 59050
    Prev
    Next
    INDEX
    Explanations

    ible

    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
    Tbl
    -0.08
     Where
    -0.08
     soften
    -0.07
     Angel
    -0.07
     côte
    -0.07
     Tou
    -0.07
    tablet
    -0.07
     Zhong
    -0.07
    示
    -0.07
     subjet
    -0.07
    POSITIVE LOGITS
     invert
    0.11
     iff
    0.09
    Invert
    0.09
    invert
    0.09
    .encrypt
    0.08
     encrypt
    0.08
     clearance
    0.08
    -member
    0.08
    ვ
    0.08
     existence
    0.08
    Activations Density 0.012%

    No Known Activations