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. 58432
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Sor
    -0.08
    /pass
    -0.08
     Eusk
    -0.08
     pensez
    -0.08
     Authority
    -0.08
    jas
    -0.08
     Navarra
    -0.07
     voucher
    -0.07
     sor
    -0.07
     Tags
    -0.07
    POSITIVE LOGITS
    cerning
    0.07
    Besides
    0.07
    طور
    0.07
     erhe
    0.07
     شکست
    0.07
    几年
    0.07
     shore
    0.07
    ச
    0.07
     prominently
    0.07
     quantum
    0.07
    Activations Density 0.000%

    No Known Activations