© 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. 94925
    Prev
    Next
    INDEX
    Explanations

    web design apps

    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
     hoof
    -0.08
     biopsy
    -0.08
     Toe
    -0.07
     eligible
    -0.07
     anot
    -0.07
     biops
    -0.07
     suport
    -0.07
    Ticks
    -0.07
     zaken
    -0.07
    Eligible
    -0.07
    POSITIVE LOGITS
     Airt
    0.13
    .router
    0.11
    .permission
    0.09
    	router
    0.09
    .firebase
    0.09
     routers
    0.09
     Responsive
    0.09
    (router
    0.08
    Responsive
    0.08
    .table
    0.08
    Activations Density 0.006%

    No Known Activations