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. 23-RESID-POST-AA
    6. 98454
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ৫
    -0.08
    евич
    -0.07
    際
    -0.07
     Sy
    -0.07
    V
    -0.07
    раф
    -0.07
     تفا
    -0.07
     critically
    -0.07
    -0.07
     controlling
    -0.06
    POSITIVE LOGITS
    nong
    0.10
    /io
    0.08
     Outs
    0.08
     മല
    0.08
    kert
    0.08
     nakne
    0.08
    (Runtime
    0.08
     makemake
    0.08
    েগ
    0.08
    ম্ব
    0.08
    Activations Density 0.001%

    No Known Activations