© 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. 65484
    Prev
    Next
    INDEX
    Explanations

    leprosy

    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
    illiance
    -0.08
     equipamento
    -0.08
    ีน
    -0.08
    ীদের
    -0.08
    whole
    -0.07
     ukuhl
    -0.07
     tø
    -0.07
     ador
    -0.07
     partidas
    -0.07
     NIV
    -0.07
    POSITIVE LOGITS
     latency
    0.08
     geleden
    0.08
    0.07
     decide
    0.07
     décide
    0.07
     Abraham
    0.07
     Cliquez
    0.07
    /action
    0.07
    Clk
    0.07
    ौर
    0.07
    Activations Density 0.000%
    No Known Activations