© 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. 79046
    Prev
    Next
    INDEX
    Explanations

    _COMMAND

    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
     موضوع
    -0.08
     buch
    -0.08
     mada
    -0.08
    ARED
    -0.08
     Nuk
    -0.07
     вельмі
    -0.07
    .Total
    -0.07
     estup
    -0.07
    ора
    -0.07
    Pref
    -0.07
    POSITIVE LOGITS
     yuan
    0.09
     legislative
    0.08
     féminin
    0.08
     zipcode
    0.08
     annotations
    0.08
    	dest
    0.08
     legislation
    0.08
     veranderingen
    0.08
     columnist
    0.08
    额度
    0.08
    Activations Density 0.001%

    No Known Activations