© 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. 3-RESID-POST-AA
    11. 2719
    Prev
    Next
    INDEX
    Explanations

    (float

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    incy
    -0.09
     downfall
    -0.08
     revol
    -0.08
     MCA
    -0.08
     ech
    -0.08
     XO
    -0.08
    	ar
    -0.08
     Lei
    -0.07
    imson
    -0.07
    娜
    -0.07
    POSITIVE LOGITS
     gilt
    0.07
     supermarket
    0.07
    ustra
    0.07
     fridge
    0.07
    ength
    0.07
     motto
    0.07
    meti
    0.07
     palindrome
    0.07
    必
    0.07
    -upper
    0.07
    Activations Density 0.001%

    No Known Activations