© 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. 23-RESID-POST-AA
    11. 48802
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ence"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     لینے
    -0.08
    /activity
    -0.08
     港
    -0.08
     มาก
    -0.08
     바이
    -0.08
    .Preference
    -0.08
    .SQL
    -0.08
    层
    -0.08
    ılım
    -0.08
     �
    -0.08
    POSITIVE LOGITS
    ency
    0.11
    ence
    0.09
    encies
    0.09
    icos
    0.09
    ently
    0.08
     asesor
    0.08
    enter
    0.08
    encia
    0.08
     triangle
    0.08
    od
    0.08
    Activations Density 0.001%

    No Known Activations