© 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. 11-RESID-POST-AA
    11. 25015
    Prev
    Next
    INDEX
    Explanations

    Ramen recipes

    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
    ელები
    -0.08
    (embed
    -0.08
     Vai
    -0.08
    _js
    -0.08
     Catalunya
    -0.08
     деньги
    -0.08
     الالكتر
    -0.07
    色
    -0.07
     Nett
    -0.07
    იანი
    -0.07
    POSITIVE LOGITS
     zwe
    0.07
     gracia
    0.07
    ategorical
    0.07
    tpl
    0.07
    .Unmarshal
    0.07
     desfile
    0.07
    pm
    0.07
     soepel
    0.07
     плав
    0.07
    fitness
    0.07
    Activations Density 0.002%

    No Known Activations