© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30158
    Prev
    Next
    INDEX
    Explanations

    Pacific Islands

    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
    Fee
    -0.08
     fee
    -0.08
     filings
    -0.08
    Preco
    -0.08
    reman
    -0.08
     definição
    -0.08
    Preço
    -0.08
     Fee
    -0.08
    (mon
    -0.08
    _fee
    -0.08
    POSITIVE LOGITS
     Hawaiian
    0.13
     Polyn
    0.11
     Māori
    0.11
    菲律宾
    0.11
     lagoon
    0.11
     hapa
    0.10
     kokos
    0.10
     hoʻop
    0.10
     wahine
    0.10
     Papua
    0.10
    Activations Density 0.022%

    No Known Activations