© 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. 30921
    Prev
    Next
    INDEX
    Explanations

    simple, easy

    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
     vendors
    -0.09
     fornecedores
    -0.08
    查看更多
    -0.08
    թ
    -0.08
    -0.08
     hars
    -0.08
     específicamente
    -0.08
    .tint
    -0.08
    .more
    -0.08
     Restoration
    -0.07
    POSITIVE LOGITS
     straightforward
    0.11
    leetcode
    0.10
     Aufgabe
    0.08
    ই
    0.08
     pretty
    0.08
    ändig
    0.08
    847
    0.08
     Auss
    0.08
     Weis
    0.08
    !\
    0.07
    Activations Density 0.058%
    No Known Activations