© 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. 78210
    Prev
    Next
    INDEX
    Explanations

    water inflow

    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
     etiquette
    -0.07
    sav
    -0.07
    	case
    -0.07
    ustr
    -0.06
     UBS
    -0.06
     salvar
    -0.06
     이하
    -0.06
     cobr
    -0.06
    型
    -0.06
    -0.06
    POSITIVE LOGITS
     influx
    0.16
     поступ
    0.13
     feeding
    0.12
    incoming
    0.12
     स्रोत
    0.12
    來源
    0.12
     incoming
    0.12
     replenish
    0.12
     provenant
    0.12
     replen
    0.12
    Activations Density 0.022%
    No Known Activations