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. 77294
    Prev
    Next
    INDEX
    Explanations

    "<"

    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
     Miz
    -0.08
     Grö
    -0.08
     ez
    -0.08
    bero
    -0.08
     Kem
    -0.08
     COUN
    -0.07
     itu
    -0.07
     airfare
    -0.07
     Mum
    -0.07
     améric
    -0.07
    POSITIVE LOGITS
    မြ
    0.07
    /n
    0.07
    abcdefghijklmnopqrstuvwxyz
    0.07
    abc
    0.07
    qid
    0.07
     З
    0.07
     Ваш
    0.07
    ကြ
    0.07
     स्
    0.07
    ahir
    0.07
    Activations Density 0.001%

    No Known Activations