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. 67527
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    Are
    -0.08
    Take
    -0.08
     comentário
    -0.08
     odo
    -0.07
     Eagle
    -0.07
    assword
    -0.07
     Stockton
    -0.07
     softball
    -0.07
     regards
    -0.07
    男
    -0.07
    POSITIVE LOGITS
    特点
    0.11
     Features
    0.10
     લાભ
    0.10
    features
    0.09
    特徴
    0.09
     Benefits
    0.09
    benef
    0.09
     FEATURES
    0.09
     Vorteile
    0.09
    :↵
    0.08
    Activations Density 0.120%

    No Known Activations