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. 88250
    Prev
    Next
    INDEX
    Explanations

    P

    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
     anth
    -0.08
     Lawrence
    -0.08
     Loc
    -0.08
    yntax
    -0.07
    .w
    -0.07
     locale
    -0.07
     founding
    -0.07
     bloom
    -0.07
     affiliate
    -0.07
     Vineyard
    -0.07
    POSITIVE LOGITS
     lim
    0.09
    tout
    0.08
    东
    0.08
     boton
    0.08
    PACE
    0.08
    icie
    0.07
     Yo
    0.07
     Tout
    0.07
    todos
    0.07
     engenharia
    0.07
    Activations Density 0.001%

    No Known Activations