© 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. 68282
    Prev
    Next
    INDEX
    Explanations

    preventive

    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
    akker
    -0.08
     difficulties
    -0.08
     io
    -0.08
    (io
    -0.07
    	io
    -0.07
     Gour
    -0.07
     Poems
    -0.07
     Nets
    -0.07
     पंज
    -0.07
    #ac
    -0.07
    POSITIVE LOGITS
     prophyl
    0.13
     preventive
    0.12
     preventative
    0.12
     outpatient
    0.09
     зрения
    0.09
     counseling
    0.09
     steril
    0.09
     профилакти
    0.08
     Medicare
    0.08
    prevent
    0.08
    Activations Density 0.002%

    No Known Activations