© 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. 47666
    Prev
    Next
    INDEX
    Explanations

    non english and medical

    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
     cafeter
    -0.09
    Revenue
    -0.08
     Revenue
    -0.08
     revenue
    -0.08
    Templates
    -0.08
     begro
    -0.07
     boilers
    -0.07
     brainstorming
    -0.07
     Boilers
    -0.07
    	prop
    -0.07
    POSITIVE LOGITS
     neurop
    0.16
     nerves
    0.15
     nerve
    0.15
     neurological
    0.14
     neurolog
    0.11
     neurons
    0.11
     numb
    0.11
     spinal
    0.10
     neuro
    0.10
     acupuncture
    0.10
    Activations Density 0.023%

    No Known Activations