© 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. 26571
    Prev
    Next
    INDEX
    Explanations

    ice

    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
     educativo
    -0.09
     pala
    -0.08
     educativas
    -0.08
     spine
    -0.08
     político
    -0.07
    Ha
    -0.07
    _notify
    -0.07
     educativos
    -0.07
     الساعة
    -0.07
     Hak
    -0.07
    POSITIVE LOGITS
     gamblers
    0.08
     unde
    0.07
     dəyiş
    0.07
    odus
    0.07
     válto
    0.07
     முக்கிய
    0.07
    變
    0.07
    vál
    0.07
     UNDER
    0.07
     পরিবর্ত
    0.07
    Activations Density 0.000%

    No Known Activations