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. 42040
    Prev
    Next
    INDEX
    Explanations

    Chinese imagery, qipao

    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
     lukt
    -0.09
     Gj
    -0.08
    839
    -0.08
     cops
    -0.08
     skier
    -0.08
    bike
    -0.08
    زه
    -0.08
    labs
    -0.08
     rewarding
    -0.08
     biker
    -0.08
    POSITIVE LOGITS
    оид
    0.08
    -shaped
    0.08
    Extension
    0.08
     disadvantages
    0.08
    -style
    0.07
    ودی
    0.07
     Extension
    0.07
     изменения
    0.07
     advancements
    0.07
    Unsupported
    0.07
    Activations Density 0.002%

    No Known Activations