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. 12807
    Prev
    Next
    INDEX
    Explanations

    makeup and cosmetics

    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
     MSS
    -0.08
    liegen
    -0.08
    心经
    -0.08
     Useful
    -0.08
     Brest
    -0.08
    uriye
    -0.07
     размеров
    -0.07
     czy
    -0.07
    ികൾ
    -0.07
    mq
    -0.07
    POSITIVE LOGITS
     hiring
    0.09
    0.08
     faux
    0.07
     amino
    0.07
     sales
    0.07
     enough
    0.07
    ברה
    0.07
     salar
    0.07
     nrog
    0.07
     poudre
    0.07
    Activations Density 0.002%

    No Known Activations