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. 54103
    Prev
    Next
    INDEX
    Explanations

    software configuration

    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
     portals
    -0.08
     sorrow
    -0.08
     gug
    -0.07
     classification
    -0.07
     whereabouts
    -0.07
     costas
    -0.07
     Orient
    -0.07
     Loy
    -0.07
    -0.07
     lupus
    -0.07
    POSITIVE LOGITS
     Adjustable
    0.11
    整数
    0.11
    .Maximum
    0.11
     angka
    0.11
     instelling
    0.10
    (integer
    0.10
    .Minimum
    0.10
     adjustable
    0.10
     اندازه
    0.10
     integer
    0.10
    Activations Density 0.045%

    No Known Activations