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. 98544
    Prev
    Next
    INDEX
    Explanations

    transepidermal water loss

    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
    'p
    -0.08
     SKU
    -0.08
    լ
    -0.07
    _OPT
    -0.07
    _ALWAYS
    -0.07
     optim
    -0.07
     By
    -0.07
    кет
    -0.07
     POL
    -0.07
    bler
    -0.07
    POSITIVE LOGITS
     welches
    0.09
     specif
    0.08
     autonomy
    0.08
    asc
    0.08
     автоном
    0.08
     acaba
    0.08
    判断
    0.08
    dua
    0.08
    dep
    0.08
     autonom
    0.07
    Activations Density 0.001%

    No Known Activations