© 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. 45629
    Prev
    Next
    INDEX
    Explanations

    largest

    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
     postpartum
    -0.08
    置
    -0.07
     expresar
    -0.07
     pathways
    -0.07
     coerc
    -0.07
     premises
    -0.07
     labor
    -0.07
    idur
    -0.07
    _ABORT
    -0.07
     literals
    -0.07
    POSITIVE LOGITS
    |max
    0.08
     Divide
    0.08
    =max
    0.08
    (Max
    0.08
    ,max
    0.08
     tert
    0.08
     最大
    0.07
    సారి
    0.07
     stink
    0.07
     Write
    0.07
    Activations Density 0.026%

    No Known Activations