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. 11973
    Prev
    Next
    INDEX
    Explanations

    Medical procedures/conditions

    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
     envers
    -0.09
    ystate
    -0.08
     overhaul
    -0.08
    入力
    -0.08
    メール
    -0.08
     paroles
    -0.08
     hardships
    -0.08
     fatalities
    -0.08
     email
    -0.08
     successes
    -0.07
    POSITIVE LOGITS
     tumors
    0.15
     benign
    0.14
     опух
    0.13
     aneur
    0.12
     tumor
    0.10
     lesions
    0.10
     schw
    0.10
     सौ
    0.09
     chirurg
    0.09
     nests
    0.09
    Activations Density 0.019%

    No Known Activations