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. 54179
    Prev
    Next
    INDEX
    Explanations

    formulas and code

    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
     Litt
    -0.08
     imper
    -0.08
     ني
    -0.08
    助
    -0.08
     कठिन
    -0.08
     آخ
    -0.08
     مج
    -0.07
     تدريب
    -0.07
    OPY
    -0.07
     ری
    -0.07
    POSITIVE LOGITS
    (start
    0.09
    	start
    0.08
     spacecraft
    0.08
    ,start
    0.08
     jon
    0.07
    இத
    0.07
    [start
    0.07
     retorn
    0.07
    Pedidos
    0.07
    enzhen
    0.07
    Activations Density 0.000%

    No Known Activations