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. 15-RESID-POST-AA
    6. 19308
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     únicamente
    -0.09
    端
    -0.08
    ONLY
    -0.08
     únicos
    -0.08
    -basic
    -0.08
     gegangen
    -0.08
    いただ
    -0.08
    ある
    -0.08
    人気
    -0.07
    .origin
    -0.07
    POSITIVE LOGITS
     intermediary
    0.08
     ظاہر
    0.08
     mellan
    0.08
    entionally
    0.08
    _missing
    0.08
    cknow
    0.08
    mediate
    0.08
    linary
    0.08
     coursework
    0.08
    ellaneous
    0.08
    Activations Density 0.005%

    No Known Activations