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

    Neuronpedia

    Jacobian LensNEW
    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. 113125
    Prev
    Next
    INDEX
    Explanations

    paycheck

    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
    文字
    -0.08
     essent
    -0.08
     masih
    -0.07
     hypnot
    -0.07
     lessons
    -0.07
     koper
    -0.07
     nữ
    -0.07
     textes
    -0.07
     odnos
    -0.07
    ਵਾ
    -0.07
    POSITIVE LOGITS
    len
    0.08
     COMPLETE
    0.08
     إن
    0.08
     Arr
    0.08
    	len
    0.08
     downs
    0.07
     Enlarg
    0.07
     descuento
    0.07
    .len
    0.07
    且
    0.07
    Activations Density 0.001%

    No Known Activations