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. 12644
    Prev
    Next
    INDEX
    Explanations

    Greek mythology

    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
     περισ
    -0.09
     trails
    -0.08
     οδη
    -0.08
     flock
    -0.08
     perplex
    -0.07
     Trails
    -0.07
    _drive
    -0.07
    _Com
    -0.07
    াক
    -0.07
     driving
    -0.07
    POSITIVE LOGITS
    legal
    0.07
    JS
    0.07
    overflow
    0.07
    祖
    0.07
    г
    0.07
    -fed
    0.07
    多少钱
    0.07
    даў
    0.07
    Overflow
    0.07
    Atom
    0.07
    Activations Density 0.000%

    No Known Activations