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. 112860
    Prev
    Next
    INDEX
    Explanations

    in

    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
    组选
    -0.09
    mund
    -0.09
    offs
    -0.08
     marg
    -0.08
     äußer
    -0.08
    uttu
    -0.08
     groceries
    -0.07
     веществ
    -0.07
    aitheamh
    -0.07
     INCIDENTAL
    -0.07
    POSITIVE LOGITS
    数量
    0.14
    _locations
    0.12
     nationwide
    0.11
    。截至
    0.11
     എണ്ണം
    0.11
     locations
    0.11
     Locations
    0.11
    ,全国
    0.11
    全国
    0.11
    ,截至
    0.10
    Activations Density 0.093%

    No Known Activations