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. 98477
    Prev
    Next
    INDEX
    Explanations

    say "quadratic"

    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
    .packet
    -0.08
     leases
    -0.08
    leader
    -0.08
     argues
    -0.07
     convincing
    -0.07
     leased
    -0.07
    Arguments
    -0.07
    _packets
    -0.07
    .Mobile
    -0.07
    arle
    -0.07
    POSITIVE LOGITS
     Card
    0.14
     quadratic
    0.13
    Card
    0.12
     Ferrari
    0.12
     formula
    0.12
     completing
    0.11
     solving
    0.11
     CARD
    0.11
     fórmula
    0.11
    -card
    0.10
    Activations Density 0.031%

    No Known Activations