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. 15-RESID-POST-AA
    6. 19393
    Prev
    Next
    INDEX
    Explanations

    choice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +m
    -0.08
    ());//
    -0.08
    hag
    -0.08
    (kn
    -0.08
    Interesting
    -0.08
    critic
    -0.07
     способы
    -0.07
     sposób
    -0.07
     смерти
    -0.07
    ();//
    -0.07
    POSITIVE LOGITS
     lautet
    0.09
     is
    0.09
    :↵↵
    0.09
     davon
    0.09
    答案
    0.08
     nhọrọ
    0.08
    ":↵/
    0.07
     :↵↵
    0.07
    :↵↵↵↵
    0.07
     ịh
    0.07
    Activations Density 0.002%

    No Known Activations