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. 98410
    Prev
    Next
    INDEX
    Explanations

    wooden

    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
    -Dame
    -0.08
    ITT
    -0.08
    BUF
    -0.07
    /.
    -0.07
    ця
    -0.07
    ólica
    -0.07
    穿
    -0.07
    YST
    -0.07
    ACL
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     ads
    0.09
    developer
    0.08
    developers
    0.08
    .abort
    0.08
     advertisers
    0.08
     kome
    0.08
    ads
    0.08
     adjectives
    0.08
     finalize
    0.08
     advertiser
    0.08
    Activations Density 0.001%

    No Known Activations