© 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 EvalsExportsinterp-engineNEWAPI 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. 114134
    Prev
    Next
    INDEX
    Explanations

    (

    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
    itioner
    -0.08
    -spectrum
    -0.08
    মাত্র
    -0.07
    �
    -0.07
    ANA
    -0.07
    .nom
    -0.07
    .async
    -0.07
     ath
    -0.07
    νού
    -0.07
     vantage
    -0.07
    POSITIVE LOGITS
     _(
    0.09
     XXX
    0.08
    0.08
     ame
    0.08
     �
    0.07
    위
    0.07
    金币
    0.07
    earn
    0.07
     노력
    0.07
    盖
    0.07
    Activations Density 0.043%
    No Known Activations