© 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. 26028
    Prev
    Next
    INDEX
    Explanations

    archaic language

    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
     Kenya
    -0.08
     Noise
    -0.07
     Billboard
    -0.07
     palestra
    -0.07
     Panda
    -0.07
     তৈরি
    -0.07
     CNN
    -0.07
     assaulted
    -0.07
     Likes
    -0.07
     sport
    -0.07
    POSITIVE LOGITS
     archa
    0.19
    古
    0.15
     antique
    0.14
     古
    0.13
     पुराने
    0.13
     القديمة
    0.13
    -fashioned
    0.13
     antiguos
    0.12
     antiguo
    0.12
     ancienne
    0.12
    Activations Density 0.043%

    No Known Activations