© 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. 47331
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    거
    -0.07
    Kinder
    -0.07
     HOA
    -0.07
    rounded
    -0.07
     quar
    -0.07
     видел
    -0.07
     gatos
    -0.07
     Qua
    -0.07
    টা
    -0.07
    வர்
    -0.07
    POSITIVE LOGITS
     talu
    0.08
    培
    0.08
     airlines
    0.08
     escalating
    0.07
     scalability
    0.07
    =}
    0.07
    _record
    0.07
     thereof
    0.07
     plastics
    0.07
     therein
    0.07
    Activations Density 0.019%

    No Known Activations