© 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. 108629
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous code and text

    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
     knitting
    -0.09
     mỹ
    -0.08
    ��
    -0.08
    Highlights
    -0.08
     Մենք
    -0.08
    Talking
    -0.08
     sustainability
    -0.08
     להשת
    -0.08
     nkw
    -0.08
     ಬೆಂಗಳೂರ
    -0.08
    POSITIVE LOGITS
    ח
    0.08
     itself
    0.07
     partners
    0.07
     liability
    0.07
    霍
    0.07
     lateral
    0.07
     "?
    0.07
     away
    0.07
    bination
    0.07
     '*
    0.07
    Activations Density 0.000%

    No Known Activations