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. 30754
    Prev
    Next
    INDEX
    Explanations

    RT

    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
    接
    -0.08
    涛
    -0.07
    慰
    -0.07
    名
    -0.07
    疗
    -0.07
    泰
    -0.07
     biod
    -0.07
    EOF
    -0.07
     شاید
    -0.07
     Biod
    -0.07
    POSITIVE LOGITS
     বিভাগের
    0.08
     বিভাগ
    0.08
     geh
    0.08
    _AI
    0.08
    ôtes
    0.08
     nipples
    0.08
    pheres
    0.08
     διαθέ
    0.07
    ellers
    0.07
     সক্ষম
    0.07
    Activations Density 0.002%

    No Known Activations