© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113579
    Prev
    Next
    INDEX
    Explanations

    Floors and technology

    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
     Communications
    -0.09
     communications
    -0.08
     confidentiality
    -0.08
     literary
    -0.08
     titres
    -0.08
     Headquarters
    -0.08
    /Product
    -0.08
     Guns
    -0.08
     Produit
    -0.07
     portes
    -0.07
    POSITIVE LOGITS
    踩
    0.15
     pavement
    0.14
     asphalt
    0.13
     asfalt
    0.13
     sidewalks
    0.13
     flooring
    0.12
     beneath
    0.12
    铺
    0.12
     footwear
    0.12
     gravel
    0.12
    Activations Density 0.164%

    No Known Activations