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. 11-RESID-POST-AA
    6. 60809
    Prev
    Next
    INDEX
    Explanations

    Hidden or optional elements

    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
    审批
    -0.09
    (o
    -0.08
    agua
    -0.08
    (colors
    -0.08
    (font
    -0.08
     prototype
    -0.07
    (button
    -0.07
     Legisl
    -0.07
    (color
    -0.07
    (wait
    -0.07
    POSITIVE LOGITS
     quirky
    0.08
    endor
    0.08
     bonus
    0.08
     rewarding
    0.08
    anden
    0.08
     quests
    0.08
     secluded
    0.07
    Rewards
    0.07
    allas
    0.07
     devoted
    0.07
    Activations Density 0.020%

    No Known Activations