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. 11-RESID-POST-AA
    6. 106290
    Prev
    Next
    INDEX
    Explanations

    code

    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
     monopol
    -0.08
     spanning
    -0.08
     hill
    -0.08
    Ctl
    -0.08
    invest
    -0.07
    .ol
    -0.07
     þannig
    -0.07
    _VEC
    -0.07
     italien
    -0.07
     sentirse
    -0.07
    POSITIVE LOGITS
     tiếp
    0.09
    ##_
    0.08
    areness
    0.08
     Vans
    0.08
     raws
    0.07
     htt
    0.07
    ーム
    0.07
    Wise
    0.07
     totes
    0.07
    _element
    0.07
    Activations Density 0.005%

    No Known Activations