© 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. 129544
    Prev
    Next
    INDEX
    Explanations

    sampling

    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
    ემა
    -0.08
    ენა
    -0.08
     Sart
    -0.08
    ppet
    -0.08
     há
    -0.08
    cont
    -0.07
    addr
    -0.07
    rosi
    -0.07
    amise
    -0.07
    avení
    -0.07
    POSITIVE LOGITS
    看看
    0.10
     gcd
    0.09
     Nic
    0.08
     purpos
    0.08
     súper
    0.08
     ๆ
    0.08
     Insets
    0.08
     gd
    0.08
    ساب
    0.07
     iche
    0.07
    Activations Density 0.009%

    No Known Activations