© 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. 19-RESID-POST-AA
    11. 102456
    Prev
    Next
    INDEX
    Explanations

    Con

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Particularly
    -0.09
     brilh
    -0.09
     querendo
    -0.09
     querem
    -0.09
    анса
    -0.09
     particulièrement
    -0.08
     odmah
    -0.08
     sérstaklega
    -0.08
     wanting
    -0.08
     devono
    -0.08
    POSITIVE LOGITS
     something
    0.10
     that
    0.09
     그렇게
    0.09
     it
    0.09
    stood
    0.08
    oved
    0.08
     etwas
    0.08
     these
    0.08
    -alone
    0.08
    -b
    0.08
    Activations Density 0.002%

    No Known Activations