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. 15-RESID-POST-AA
    6. 19400
    Prev
    Next
    INDEX
    Explanations

    About availability and conditions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     humorous
    -0.09
     comedic
    -0.08
    ്ത
    -0.08
    掉
    -0.08
    、省
    -0.08
    省
    -0.08
    heits
    -0.08
     hilarious
    -0.07
     ziek
    -0.07
     papild
    -0.07
    POSITIVE LOGITS
     Available
    0.10
    available
    0.10
     Regardless
    0.09
     несмотря
    0.09
     verfüg
    0.09
     Despite
    0.09
     Availability
    0.09
     available
    0.09
     Even
    0.08
     disponíveis
    0.08
    Activations Density 0.001%

    No Known Activations