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. 29969
    Prev
    Next
    INDEX
    Explanations

    Users

    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
    เช
    -0.08
     substitutions
    -0.08
    性质
    -0.08
     transformations
    -0.08
     vulnerability
    -0.08
    _IOCTL
    -0.07
     muster
    -0.07
     rota
    -0.07
     задания
    -0.07
     instrumentation
    -0.07
    POSITIVE LOGITS
     muốn
    0.12
     seeking
    0.11
     aiming
    0.11
     تبحث
    0.11
    Seeking
    0.11
     želi
    0.11
     ingin
    0.11
     الباحث
    0.11
     tired
    0.10
     ищ
    0.10
    Activations Density 0.037%

    No Known Activations