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. 60846
    Prev
    Next
    INDEX
    Explanations

    yoga breathing

    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
    šina
    -0.08
     profoundly
    -0.08
     numerous
    -0.08
    oinho
    -0.08
     vastly
    -0.08
     PD
    -0.08
     pony
    -0.08
     genees
    -0.07
     atop
    -0.07
    ôn
    -0.07
    POSITIVE LOGITS
    oce
    0.09
    -only
    0.08
     sär
    0.08
    _only
    0.08
    rib
    0.07
    _permalink
    0.07
    盐
    0.07
     ocean
    0.07
     seaw
    0.07
     盐
    0.07
    Activations Density 0.000%

    No Known Activations