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. 88168
    Prev
    Next
    INDEX
    Explanations

    code, math, technical text

    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
    .day
    -0.08
     elsewhere
    -0.08
    ,)
    -0.08
     days
    -0.08
    .month
    -0.07
     clinical
    -0.07
     months
    -0.07
    .JPG
    -0.07
    )n
    -0.07
    near
    -0.07
    POSITIVE LOGITS
    ที่จะ
    0.08
     பண
    0.08
     Vater
    0.08
     Sheriff's
    0.08
     Inflate
    0.08
     použ
    0.07
     ویژگی
    0.07
    βαι
    0.07
     بنابراین
    0.07
     رفع
    0.07
    Activations Density 0.000%

    No Known Activations