© 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. 129467
    Prev
    Next
    INDEX
    Explanations

    arithmetic

    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
    ونو
    -0.08
    +r
    -0.07
    ,r
    -0.07
     feathers
    -0.07
     بع
    -0.07
    outside
    -0.07
    ଶ
    -0.07
    (Configuration
    -0.07
    UTF
    -0.07
    ара
    -0.07
    POSITIVE LOGITS
    לך
    0.08
     hoş
    0.08
     იყოს
    0.08
    -thirds
    0.08
     三
    0.08
    总站
    0.08
    centrum
    0.08
    ζεται
    0.08
    σκεται
    0.08
    	ch
    0.08
    Activations Density 0.015%

    No Known Activations