© 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. 7-RESID-POST-AA
    11. 1368
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    versed
    -0.08
     ST
    -0.08
    uran
    -0.08
    ലയ
    -0.07
     MIN
    -0.07
    -0.07
     talent
    -0.07
     Won
    -0.07
    dow
    -0.07
    	enter
    -0.07
    POSITIVE LOGITS
    Ontario
    0.09
     researched
    0.08
    OA
    0.08
    াদি
    0.08
     verkrij
    0.07
     plur
    0.07
    折
    0.07
     Mickey
    0.07
    Ha
    0.07
     onderwerp
    0.07
    Activations Density 0.039%
    No Known Activations