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. 131000
    Prev
    Next
    INDEX
    Explanations

    of

    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
    dam
    -0.08
    нице
    -0.08
    692
    -0.08
     раск
    -0.08
    iché
    -0.08
     mysteries
    -0.07
    ોચ
    -0.07
     Stuttgart
    -0.07
    sei
    -0.07
     sticker
    -0.07
    POSITIVE LOGITS
     Haw
    0.08
     South
    0.08
    South
    0.07
     Pamp
    0.07
     estacion
    0.07
     Fläche
    0.07
     Lake
    0.07
    Hull
    0.07
     ସ
    0.07
     sick
    0.07
    Activations Density 0.003%

    No Known Activations