Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 60739
    Prev
    Next
    INDEX
    Explanations

    cafe

    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
    枚
    -0.08
    尺
    -0.08
     quart
    -0.08
     pertains
    -0.07
     إطار
    -0.07
     sacred
    -0.07
    FRAME
    -0.07
    çə
    -0.07
     Elf
    -0.07
     integrated
    -0.07
    POSITIVE LOGITS
     분위
    0.09
    💕
    0.08
     italien
    0.08
     havas
    0.08
     Consol
    0.08
     routines
    0.08
    قبال
    0.08
     dian
    0.08
     Lena
    0.08
     Valentino
    0.07
    Activations Density 0.006%

    No Known Activations