© 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. 91235
    Prev
    Next
    INDEX
    Explanations

    floating

    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
     broadcast
    -0.08
    дите
    -0.08
    zaal
    -0.08
     exploitation
    -0.08
     wind
    -0.08
    fasst
    -0.07
     broadcasts
    -0.07
    ześ
    -0.07
    ಾನ್ಯ
    -0.07
    ịa
    -0.07
    POSITIVE LOGITS
     hk
    0.07
     memor
    0.07
     madre
    0.07
    0.07
     krij
    0.07
    0.07
    ido
    0.07
     izm
    0.07
    ]['
    0.07
    owns
    0.07
    Activations Density 0.002%
    No Known Activations