Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44113
    Prev
    Next
    INDEX
    Explanations

    locations/islands

    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
     presup
    -0.08
     grinders
    -0.08
     Respons
    -0.08
    ਏ
    -0.08
     Ragnar
    -0.08
     ceremon
    -0.08
     ejempl
    -0.08
     ಸಾಗ
    -0.08
    ৰে
    -0.08
     settlers
    -0.08
    POSITIVE LOGITS
     정확
    0.08
     숙
    0.08
    브
    0.08
     никаких
    0.07
     위치
    0.07
     существует
    0.07
     point
    0.07
    bru
    0.07
     صحة
    0.07
    vil
    0.07
    Activations Density 0.024%

    No Known Activations