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. 53002
    Prev
    Next
    INDEX
    Explanations

    Deglazing recipes

    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
    तः
    -0.07
     lighting
    -0.07
    loko
    -0.07
    �
    -0.07
    _MODULE
    -0.07
    prov
    -0.07
    รีย
    -0.07
     crime
    -0.07
    IDX
    -0.07
    PLAN
    -0.07
    POSITIVE LOGITS
     tees
    0.09
     slammed
    0.08
     tslib
    0.08
    ítás
    0.08
     bevel
    0.08
    ítő
    0.08
     Wembley
    0.07
    Raz
    0.07
     DSS
    0.07
    iseerd
    0.07
    Activations Density 0.001%

    No Known Activations