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. 56037
    Prev
    Next
    INDEX
    Explanations

    -way or way

    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
     जल्दी
    -0.08
     formats
    -0.08
    ();↵
    -0.08
    甚
    -0.07
    jast
    -0.07
    突出
    -0.07
     ();↵
    -0.07
     jaz
    -0.07
     jol
    -0.07
     tails
    -0.07
    POSITIVE LOGITS
     headquartered
    0.08
    忆
    0.07
    /Test
    0.07
     MAY
    0.07
     Vans
    0.07
     invis
    0.07
     Holland
    0.07
     මෙ
    0.07
     We're
    0.07
     we're
    0.07
    Activations Density 0.000%

    No Known Activations