Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 117529
    Prev
    Next
    INDEX
    Explanations

    credit

    np_max-act · gemini-2.0-flash

    finance-related terminology, especially around lending, underwriting, and credit risk/scoring.

    oai_token-act-pair · gpt-5Triggered by @ashater
    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
    Ved
    -0.08
     wavelengths
    -0.08
    .Back
    -0.08
     Roz
    -0.08
     pigments
    -0.08
    Dropped
    -0.07
    Ink
    -0.07
    Roz
    -0.07
    Friday
    -0.07
    Nig
    -0.07
    POSITIVE LOGITS
    worthiness
    0.16
    worthy
    0.11
    额度
    0.10
     jus
    0.09
    giver
    0.08
    оспособ
    0.08
    rating
    0.08
     Santa
    0.08
     adequ
    0.08
    beer
    0.08
    Activations Density 0.009%

    No Known Activations