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. 53856
    Prev
    Next
    INDEX
    Explanations

    XL

    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
     shoulders
    -0.07
    -Sch
    -0.07
     Serra
    -0.07
     Mü
    -0.07
    帶
    -0.07
    \Json
    -0.07
     കാരണം
    -0.07
    Qs
    -0.07
    -0.07
     sch
    -0.06
    POSITIVE LOGITS
    Forg
    0.08
    های
    0.08
    iyalar
    0.08
     Forg
    0.08
    იურ
    0.08
    Looks
    0.08
    nya
    0.07
    ан
    0.07
    אַסט
    0.07
     locksmith
    0.07
    Activations Density 0.000%

    No Known Activations