© 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. 19-RESID-POST-AA
    11. 102417
    Prev
    Next
    INDEX
    Explanations

    Ethical sourcing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	template
    -0.08
     Zw
    -0.08
    _template
    -0.08
     RK
    -0.07
    模板
    -0.07
     万
    -0.07
    [++
    -0.07
     ZX
    -0.07
     Künd
    -0.07
    tpl
    -0.07
    POSITIVE LOGITS
     sourcing
    0.21
     provenance
    0.18
     происх
    0.18
     Herkunft
    0.17
     terro
    0.16
     ethically
    0.16
     sustainably
    0.16
     sourced
    0.16
    來源
    0.16
    采购
    0.16
    Activations Density 0.062%

    No Known Activations