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. 120337
    Prev
    Next
    INDEX
    Explanations

    finance and transactions

    np_max-act · gemini-2.0-flash

    phrases that advertise commercial actions or offers (words like buy, earn, download, drive).

    oai_token-act-pair · gpt-5-miniTriggered by @mlfinancebook

    hyphenated phrasal constructions and verb–particle compounds (e.g., action-oriented “X–particle” forms) indicating events, processes, or transactional actions.

    oai_token-act-pair · gpt-5Triggered 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
     ecu
    -0.09
    uncan
    -0.08
     elector
    -0.08
    zyst
    -0.08
     devons
    -0.08
    /temp
    -0.08
     वृ
    -0.08
    supplier
    -0.08
     transient
    -0.08
     रस
    -0.08
    POSITIVE LOGITS
    -up
    0.14
    -down
    0.13
    -through
    0.12
    -back
    0.12
    -outs
    0.12
    -out
    0.12
    -off
    0.12
    -offs
    0.11
    -away
    0.11
    -in
    0.11
    Activations Density 0.102%

    No Known Activations