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. 11924
    Prev
    Next
    INDEX
    Explanations

    not

    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
     nonetheless
    -0.08
     lediglich
    -0.08
    'hôtel
    -0.08
     zwar
    -0.08
    Black
    -0.08
     hice
    -0.08
     bereits
    -0.07
    .pb
    -0.07
     Hull
    -0.07
     futuros
    -0.07
    POSITIVE LOGITS
    odas
    0.08
     volume
    0.08
    �
    0.08
     fell
    0.08
     gerekiyor
    0.08
     stamina
    0.08
     scalable
    0.07
    falls
    0.07
     Falls
    0.07
     Volume
    0.07
    Activations Density 0.019%

    No Known Activations