© 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. 102190
    Prev
    Next
    INDEX
    Explanations

    of

    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
     millis
    -0.08
     MW
    -0.08
    CSA
    -0.08
    .organization
    -0.08
     combined
    -0.08
     mot
    -0.07
     proposés
    -0.07
     organización
    -0.07
    报名
    -0.07
     args
    -0.07
    POSITIVE LOGITS
     bizarre
    0.10
     wildly
    0.09
     horrifying
    0.09
     bataille
    0.09
     alterar
    0.09
    continence
    0.09
     confront
    0.08
     dramatically
    0.08
     compromising
    0.08
     alarming
    0.08
    Activations Density 0.004%

    No Known Activations