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. 88143
    Prev
    Next
    INDEX
    Explanations

    payments or cash

    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
     velen
    -0.07
     ensured
    -0.07
     trap
    -0.07
     hashtag
    -0.07
     editorial
    -0.07
     chamber
    -0.07
     esperar
    -0.07
     hashtags
    -0.07
     expand
    -0.07
    জাত
    -0.07
    POSITIVE LOGITS
    偿
    0.13
     repayment
    0.11
    缴
    0.11
     Debt
    0.11
     राशि
    0.11
     payments
    0.10
     قرض
    0.10
    Debt
    0.10
     debt
    0.10
     repayments
    0.10
    Activations Density 0.018%

    No Known Activations