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. 23-RESID-POST-AA
    6. 98090
    Prev
    Next
    INDEX
    Explanations

    training programs

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ánimo
    -0.09
     leisurely
    -0.08
    בער
    -0.08
    (Bitmap
    -0.08
     deodor
    -0.08
    endants
    -0.08
     serene
    -0.08
    شاط
    -0.08
    flix
    -0.08
     早餐
    -0.08
    POSITIVE LOGITS
     period
    0.14
     programmation
    0.13
     programming
    0.13
     volume
    0.13
    Programming
    0.13
    Period
    0.12
    Volume
    0.12
     stimulus
    0.12
     adaptations
    0.12
    volume
    0.12
    Activations Density 0.041%

    No Known Activations