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. 11968
    Prev
    Next
    INDEX
    Explanations

    by

    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
     lectura
    -0.08
     bezeichnet
    -0.07
    350
    -0.07
     تعتمد
    -0.07
     maß
    -0.07
     القراءة
    -0.07
    yrus
    -0.07
     Bl
    -0.07
     vuestro
    -0.07
     faucibus
    -0.07
    POSITIVE LOGITS
     李
    0.09
     evas
    0.08
     salvar
    0.08
     鑫
    0.08
    umit
    0.08
    istar
    0.08
    鹅
    0.08
     നിയ
    0.08
    _evt
    0.08
     星际
    0.08
    Activations Density 0.000%

    No Known Activations