© 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. 25141
    Prev
    Next
    INDEX
    Explanations

    verbs

    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
     Goodreads
    -0.09
     decades
    -0.09
     user's
    -0.08
    �
    -0.08
     lifespan
    -0.08
     lifetime
    -0.08
     подарок
    -0.08
     centuries
    -0.08
     eeuwen
    -0.08
    lys
    -0.08
    POSITIVE LOGITS
     overnight
    0.12
     afternoon
    0.11
     মঙ্গলবার
    0.11
     Monday
    0.11
     सोमवार
    0.10
     evening
    0.10
     midday
    0.10
     সোমবার
    0.10
     crews
    0.10
     minggu
    0.10
    Activations Density 0.115%

    No Known Activations