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. 11957
    Prev
    Next
    INDEX
    Explanations

    language

    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
    _syn
    -0.08
    LED
    -0.08
    ilot
    -0.08
    -flat
    -0.07
    empot
    -0.07
    _modified
    -0.07
    改
    -0.07
    _feedback
    -0.07
    _flat
    -0.07
    =min
    -0.07
    POSITIVE LOGITS
     langues
    0.13
     idiomas
    0.13
     étrangères
    0.11
     Languages
    0.10
     দক্ষ
    0.10
    Languages
    0.10
     compétences
    0.10
     الأجنبية
    0.10
     languages
    0.09
     валют
    0.09
    Activations Density 0.023%

    No Known Activations