© 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. 3-RESID-POST-AA
    11. 2878
    Prev
    Next
    INDEX
    Explanations

    nutshell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Colonial
    -0.08
    -maker
    -0.08
    (generator
    -0.07
    quelize
    -0.07
    irections
    -0.07
     genital
    -0.07
     aloj
    -0.07
    operator
    -0.07
     CGRect
    -0.07
    nonatomic
    -0.07
    POSITIVE LOGITS
     пом
    0.08
     подробнее
    0.08
     Groot
    0.08
     forge
    0.08
     firmly
    0.08
     trem
    0.08
    .tp
    0.07
     путем
    0.07
     ач
    0.07
    째
    0.07
    Activations Density 0.000%

    No Known Activations