© 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. 23-RESID-POST-AA
    11. 6391
    Prev
    Next
    INDEX
    Explanations

    с

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ies
    -0.09
    zina
    -0.08
    illis
    -0.08
    zie
    -0.08
    isées
    -0.08
    arlu
    -0.08
    ileri
    -0.08
     pesticides
    -0.08
     nasa
    -0.08
    ieuses
    -0.07
    POSITIVE LOGITS
    ू
    0.09
    ovalo
    0.09
    увати
    0.08
    ੂ
    0.08
    പ്പെട്ടു
    0.08
    ؤ
    0.08
    üml
    0.08
    പ്പെടുത്തി
    0.08
    ують
    0.08
     Hoop
    0.07
    Activations Density 0.000%

    No Known Activations