© 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. 44927
    Prev
    Next
    INDEX
    Explanations

    to

    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
    704
    -0.08
     және
    -0.07
     жыл
    -0.07
     முத
    -0.07
     жаң
    -0.07
    收益
    -0.07
    714
    -0.07
    itz
    -0.07
    周期
    -0.07
     ප්
    -0.07
    POSITIVE LOGITS
     startled
    0.09
     себя
    0.09
     siebie
    0.09
    Everyone
    0.08
    নিক
    0.08
     gern
    0.08
    Equipe
    0.08
    agnie
    0.08
     surprised
    0.08
     ogl
    0.08
    Activations Density 0.007%

    No Known Activations