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. 112879
    Prev
    Next
    INDEX
    Explanations

    Oat milk

    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
     Tore
    -0.09
    _comp
    -0.07
    _locked
    -0.07
     경쟁
    -0.07
    COMP
    -0.07
    竞争
    -0.07
    _com
    -0.07
    ajr
    -0.07
    _lock
    -0.07
     그
    -0.07
    POSITIVE LOGITS
    Wise
    0.08
    led
    0.08
     расход
    0.08
     équilibr
    0.08
     crafts
    0.08
     extravagant
    0.08
     caching
    0.08
     objections
    0.08
     cheapest
    0.07
     výro
    0.07
    Activations Density 0.001%

    No Known Activations