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. 7-RESID-POST-AA
    6. 131040
    Prev
    Next
    INDEX
    Explanations

    )!

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    خم
    -0.09
     sat
    -0.08
     устойчив
    -0.08
     سات
    -0.07
     proactive
    -0.07
     ferrovi
    -0.07
    মাত্র
    -0.07
     moisture
    -0.07
     способ
    -0.07
     о
    -0.07
    POSITIVE LOGITS
     UAE
    0.08
    EA
    0.08
    Arn
    0.08
    0.07
    ála
    0.07
     EA
    0.07
    ","+
    0.07
    (E
    0.07
     gigantic
    0.07
    ulong
    0.07
    Activations Density 0.003%

    No Known Activations