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. 44982
    Prev
    Next
    INDEX
    Explanations

    algorithm analysis

    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
    Guid
    -0.09
     realities
    -0.08
     compromises
    -0.08
     혁
    -0.08
    -workers
    -0.07
     abond
    -0.07
     compromis
    -0.07
     birt
    -0.07
     manifi
    -0.07
    😭
    -0.07
    POSITIVE LOGITS
     التح
    0.09
     straightforward
    0.09
    ดำ
    0.08
     leisurely
    0.08
    ANA
    0.08
     ط
    0.08
     upfront
    0.08
     costume
    0.08
     logo
    0.07
     einfache
    0.07
    Activations Density 0.002%

    No Known Activations