© 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. 63782
    Prev
    Next
    INDEX
    Explanations

    Names/initials/abbreviations

    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
    agd
    -0.08
    resar
    -0.08
     dispensing
    -0.07
    ाढ़
    -0.07
    _SD
    -0.07
    ，上
    -0.07
     consolation
    -0.07
    duled
    -0.07
     Spanien
    -0.07
     hiçbir
    -0.07
    POSITIVE LOGITS
     Roosevelt
    0.09
     Fortnite
    0.08
     Barack
    0.08
    ampp
    0.08
     Collapse
    0.08
     Tolkien
    0.08
     Bay
    0.07
     الله
    0.07
    ax
    0.07
     Nietzsche
    0.07
    Activations Density 0.230%

    No Known Activations