© 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. 63605
    Prev
    Next
    INDEX
    Explanations

    marketing, SEO, launch

    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
    wọn
    -0.09
     볼
    -0.08
    Measurements
    -0.07
     tov
    -0.07
     Scalar
    -0.07
     আলো
    -0.07
     Хот
    -0.07
     данной
    -0.07
    ające
    -0.07
     shall
    -0.07
    POSITIVE LOGITS
     profitable
    0.10
     embarrassing
    0.10
     obsessed
    0.09
    创业
    0.09
     overpriced
    0.09
    赚
    0.09
     bankroll
    0.09
    赚钱
    0.09
    DIY
    0.09
     entrepreneurship
    0.09
    Activations Density 0.033%

    No Known Activations