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. 45079
    Prev
    Next
    INDEX
    Explanations

    park

    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
    办公
    -0.09
     cumbersome
    -0.08
     процедур
    -0.08
     kayıt
    -0.08
     Fu
    -0.08
    备
    -0.08
     Atlético
    -0.08
     oficinas
    -0.08
    复
    -0.08
    约
    -0.07
    POSITIVE LOGITS
     joke
    0.09
    torrent
    0.09
     zombie
    0.08
     sate
    0.08
     ebook
    0.08
     veng
    0.08
     comics
    0.08
     comic
    0.08
     fist
    0.08
     gira
    0.08
    Activations Density 0.001%

    No Known Activations