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. 98352
    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
    taine
    -0.08
    iven
    -0.07
    griffen
    -0.07
     dioc
    -0.07
    EDITOR
    -0.07
    .le
    -0.07
    Viewer
    -0.07
     本
    -0.07
     xyz
    -0.07
    tdy
    -0.07
    POSITIVE LOGITS
    ంశ
    0.08
    Infl
    0.08
     Sorting
    0.07
    (Member
    0.07
     ప్రతి
    0.07
    ṁ
    0.07
    _member
    0.07
     agak
    0.07
     Lleg
    0.07
    (member
    0.07
    Activations Density 0.000%

    No Known Activations