© 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. 44278
    Prev
    Next
    INDEX
    Explanations

    purposely

    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
     Aquarium
    -0.08
     Communities
    -0.08
    Lifestyle
    -0.08
     Lifestyle
    -0.08
    rice
    -0.08
     Comunidad
    -0.07
     Hacienda
    -0.07
    ्रा
    -0.07
    Jeg
    -0.07
    -May
    -0.07
    POSITIVE LOGITS
     confusing
    0.09
     cunning
    0.09
     coincidence
    0.08
     misleading
    0.08
    Coin
    0.08
    SB
    0.08
     easier
    0.08
     purposely
    0.07
     coin
    0.07
    如此
    0.07
    Activations Density 0.014%

    No Known Activations