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. 130950
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    Int
    -0.09
    IF
    -0.09
     Int
    -0.08
     int
    -0.08
    _Int
    -0.08
    設定
    -0.08
    IEN
    -0.07
    spir
    -0.07
    .int
    -0.07
     Intelli
    -0.07
    POSITIVE LOGITS
    羞
    0.08
    ான
    0.08
    omende
    0.08
    ுடைய
    0.08
     Lore
    0.07
     chand
    0.07
     الاسم
    0.07
     lokasi
    0.07
     بش
    0.07
     نور
    0.07
    Activations Density 0.006%

    No Known Activations