© 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. 102540
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    <|endoftext|>
    -0.08
    (terraform
    -0.08
    "s
    -0.08
    kamp
    -0.08
    rió
    -0.07
    (图
    -0.07
    .rot
    -0.07
    лез
    -0.07
    (Audio
    -0.07
    (attributes
    -0.07
    POSITIVE LOGITS
     the
    0.08
     //
    0.07
     T
    0.07
     `
    0.07
     tmp
    0.07
     boiler
    0.07
     بـ
    0.07
    ＝＝
    0.07
     eta
    0.07
     η
    0.07
    Activations Density 0.131%

    No Known Activations