Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 130999
    Prev
    Next
    INDEX
    Explanations

    prze

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mississippi
    -0.07
     neues
    -0.07
    供
    -0.07
     conceivable
    -0.07
     tattoo
    -0.07
     Stephens
    -0.07
     Georg
    -0.07
    ischt
    -0.07
    あと
    -0.07
    kis
    -0.06
    POSITIVE LOGITS
     �
    0.08
     CIO
    0.07
    첨
    0.07
     collections
    0.07
    mie
    0.07
     Hum
    0.07
    -depth
    0.07
     arrogance
    0.07
     cand
    0.07
    ๋
    0.07
    Activations Density 0.001%

    No Known Activations