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. 7-RESID-POST-AA
    6. 131062
    Prev
    Next
    INDEX
    Explanations

    triathlon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    以来
    -0.08
     leaks
    -0.08
    VR
    -0.08
    GAL
    -0.07
     Pixel
    -0.07
    级
    -0.07
    幽
    -0.07
    LAST
    -0.07
    lá
    -0.07
    操作
    -0.07
    POSITIVE LOGITS
     综合
    0.09
     encompass
    0.08
     omvat
    0.08
    تش
    0.08
     etapa
    0.08
     snork
    0.08
    tekij
    0.08
    ienda
    0.08
    éfono
    0.08
     зрел
    0.08
    Activations Density 0.004%

    No Known Activations