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. 55984
    Prev
    Next
    INDEX
    Explanations

    can do

    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
     contabil
    -0.08
    580
    -0.08
    (dl
    -0.08
     Davies
    -0.08
     dissolved
    -0.07
    751
    -0.07
    706
    -0.07
    dl
    -0.07
    845
    -0.07
    lectricité
    -0.07
    POSITIVE LOGITS
    -after
    0.11
    -do
    0.10
    -it
    0.10
    -look
    0.09
    -a
    0.09
    -download
    0.09
    -through
    0.09
    -ара
    0.09
     mentality
    0.09
    -preview
    0.08
    Activations Density 0.051%

    No Known Activations