© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68805
    Prev
    Next
    INDEX
    Explanations

    |

    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
     silver
    -0.08
    ISI
    -0.08
    IQ
    -0.07
     Leib
    -0.07
    trail
    -0.07
     Mrs
    -0.07
    peak
    -0.07
     المؤ
    -0.07
     बनाए
    -0.07
     Ack
    -0.07
    POSITIVE LOGITS
     وذلك
    0.07
     beb
    0.07
    aira
    0.07
    还有
    0.07
     bang
    0.07
    	CC
    0.07
     mide
    0.07
     letzter
    0.07
    发表
    0.07
    Charging
    0.07
    Activations Density 0.079%

    No Known Activations