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. 15-RESID-POST-AA
    6. 165
    Prev
    Next
    INDEX
    Explanations

    Single-digit numbers

    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
     Ambas
    -0.09
    LAY
    -0.09
     दोनों
    -0.09
     Beide
    -0.08
     બંને
    -0.08
     ambas
    -0.08
     aust
    -0.08
     meglio
    -0.08
    兩
    -0.08
     καλύτε
    -0.08
    POSITIVE LOGITS
     except
    0.09
    ಿದ್ದ
    0.09
    'ing
    0.08
    તાઓ
    0.08
     presses
    0.08
    'ed
    0.08
    _count
    0.08
    .Builder
    0.08
    Except
    0.08
    _except
    0.08
    Activations Density 0.017%

    No Known Activations