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. 90167
    Prev
    Next
    INDEX
    Explanations

    APIs and 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
     Install
    -0.09
     dritte
    -0.08
     Aper
    -0.08
     Polytechnic
    -0.08
     grassroots
    -0.08
     enthous
    -0.08
    Basics
    -0.08
    Install
    -0.08
    Installing
    -0.08
     Efter
    -0.08
    POSITIVE LOGITS
     let
    0.08
     underlying
    0.08
     lop
    0.07
    ps
    0.07
     lec
    0.07
     just
    0.07
    .Byte
    0.07
     secular
    0.07
     ld
    0.07
    лед
    0.07
    Activations Density 0.000%

    No Known Activations