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. 130922
    Prev
    Next
    INDEX
    Explanations

    Backslashes

    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
     ||
    -0.09
    kate
    -0.09
     <!--
    -0.09
     !=
    -0.09
     PERIOD
    -0.08
    entor
    -0.08
     Period
    -0.08
     PLACE
    -0.08
    ent
    -0.08
    का
    -0.08
    POSITIVE LOGITS
    �
    0.11
    \Framework
    0.11
    \
    0.10
    ║
    0.10
     \
    0.10
    \Controllers
    0.10
    �
    0.09
     streaming
    0.09
    $\
    0.09
     నిర్వ
    0.09
    Activations Density 0.004%

    No Known Activations