© 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. 103186
    Prev
    Next
    INDEX
    Explanations

    1

    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
    iedad
    -0.09
    ۰۰
    -0.08
     stendur
    -0.08
    兩
    -0.08
    -two
    -0.08
     två
    -0.08
    woman
    -0.08
    .some
    -0.08
     voisi
    -0.08
    .two
    -0.08
    POSITIVE LOGITS
    ندگان
    0.08
     degene
    0.07
     surveying
    0.07
     lu
    0.07
     passive
    0.07
    associated
    0.07
     encant
    0.07
    ослав
    0.07
     sepanjang
    0.07
    داول
    0.07
    Activations Density 0.002%

    No Known Activations