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. 67332
    Prev
    Next
    INDEX
    Explanations

    yd

    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
    ...',
    -0.08
    ...",
    -0.08
    Lanc
    -0.08
    mutable
    -0.08
    кою
    -0.08
    /xml
    -0.07
     Fallen
    -0.07
     tombe
    -0.07
    :",
    -0.07
     pensions
    -0.07
    POSITIVE LOGITS
     vibe
    0.08
     belangrijk
    0.08
     permit
    0.08
     role
    0.08
     wichtig
    0.07
    anh
    0.07
     মে
    0.07
     역할
    0.07
    posaż
    0.07
    角色
    0.07
    Activations Density 0.000%

    No Known Activations