© 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. 65321
    Prev
    Next
    INDEX
    Explanations

    change

    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
     устанавли
    -0.08
     discretion
    -0.08
    Bloom
    -0.08
     Bloom
    -0.07
     delas
    -0.07
     (*)
    -0.07
    OFF
    -0.07
     Booth
    -0.07
     Bang
    -0.07
    fred
    -0.07
    POSITIVE LOGITS
     climate
    0.13
     Climate
    0.12
     exacerb
    0.12
    Climate
    0.11
     exacer
    0.11
     impacts
    0.11
     климат
    0.11
     climatic
    0.11
     forecasts
    0.11
     climates
    0.11
    Activations Density 0.022%

    No Known Activations