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. 130982
    Prev
    Next
    INDEX
    Explanations

    Finance

    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
     instructors
    -0.10
    dyž
    -0.10
     apprentice
    -0.09
    orithms
    -0.09
     ergonomic
    -0.09
     apprentices
    -0.09
    ynomial
    -0.09
     adject
    -0.08
     शिक्षक
    -0.08
     instructor
    -0.08
    POSITIVE LOGITS
    融资
    0.18
    资金
    0.17
    本金
    0.14
    债
    0.14
    现金
    0.13
    套利
    0.12
    基金
    0.12
     liquidity
    0.12
    资本
    0.12
     التمو
    0.12
    Activations Density 0.044%

    No Known Activations