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. 112820
    Prev
    Next
    INDEX
    Explanations

    point

    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
    wah
    -0.08
    asel
    -0.08
     airing
    -0.08
    automation
    -0.08
     vulputate
    -0.08
     automation
    -0.08
    Automation
    -0.08
     Automation
    -0.07
     Baking
    -0.07
     pharmacie
    -0.07
    POSITIVE LOGITS
    .points
    0.11
    _points
    0.11
     نقاط
    0.10
    punkte
    0.10
     points
    0.10
    Points
    0.10
     nokt
    0.09
    .scatter
    0.09
     точки
    0.09
     Points
    0.09
    Activations Density 0.013%

    No Known Activations