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. 75974
    Prev
    Next
    INDEX
    Explanations

    Two-digit numbers & digits

    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
     Pamela
    -0.08
     openly
    -0.07
    _arm
    -0.07
     Magna
    -0.07
    _z
    -0.07
    -Dame
    -0.07
    ত্ত
    -0.07
     talla
    -0.07
     Massive
    -0.06
    umme
    -0.06
    POSITIVE LOGITS
    .combine
    0.10
     investir
    0.08
    operand
    0.08
     receiver
    0.08
    іміз
    0.08
     onset
    0.08
    .Compose
    0.07
    Compose
    0.07
    "use
    0.07
    logout
    0.07
    Activations Density 0.015%

    No Known Activations