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. 15-RESID-POST-AA
    6. 115
    Prev
    Next
    INDEX
    Explanations

    the

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lên
    -0.08
     nuo
    -0.08
    灭
    -0.08
    。那么
    -0.08
     внимательно
    -0.08
     suppl
    -0.08
     लिह
    -0.07
     bek
    -0.07
     Mr
    -0.07
    ूप
    -0.07
    POSITIVE LOGITS
    IKA
    0.09
    这里
    0.09
    YG
    0.09
    cknow
    0.09
    ここ
    0.09
     ఇంద
    0.09
    YW
    0.08
     սա
    0.08
     এজন
    0.08
    aa
    0.08
    Activations Density 0.041%

    No Known Activations