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. 111790
    Prev
    Next
    INDEX
    Explanations

    finance and economics

    np_max-act · gemini-2.0-flash

    This neuron detects dates/years and macroeconomic/financial terms (years, timestamps and words about inflation, interest rates, markets and monetary policy).

    oai_token-act-pair · gpt-5-miniTriggered by @tatsatx
    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
     भक्त
    -0.09
    ummi
    -0.08
     daß
    -0.08
     Biography
    -0.08
     посвящ
    -0.08
    Sentence
    -0.07
     obedient
    -0.07
    ług
    -0.07
     sentence
    -0.07
    tnie
    -0.07
    POSITIVE LOGITS
    ২০২
    0.09
     DRO
    0.09
     ransomware
    0.08
    202
    0.08
    .g
    0.08
     exacerb
    0.08
    tea
    0.08
    .Drop
    0.08
    前年
    0.08
    יא
    0.08
    Activations Density 0.054%

    No Known Activations