© 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. 78343
    Prev
    Next
    INDEX
    Explanations

    translation/foreign languages

    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
     Exercise
    -0.08
     borne
    -0.08
     accordance
    -0.08
    Carte
    -0.08
     ремонт
    -0.07
     Cleanup
    -0.07
     bore
    -0.07
     Carte
    -0.07
     remed
    -0.07
     L
    -0.07
    POSITIVE LOGITS
    ถึง
    0.08
     hearings
    0.08
    砂
    0.08
    efined
    0.08
     Hear
    0.07
     سب
    0.07
    ことで
    0.07
     الد
    0.07
     सब
    0.07
     دے
    0.07
    Activations Density 0.006%

    No Known Activations