© 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. 15-RESID-POST-AA
    11. 16521
    Prev
    Next
    INDEX
    Explanations

    ,

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಅಥವಾ
    -0.08
    &iacute
    -0.08
    nand
    -0.08
    436
    -0.08
     atanapi
    -0.08
    .Func
    -0.08
     atawa
    -0.08
    enkins
    -0.08
    /she
    -0.08
     oder
    -0.08
    POSITIVE LOGITS
    Overall
    0.09
     Overall
    0.08
     Rav
    0.08
     Raven
    0.07
     overall
    0.07
    0.07
     మొత్తం
    0.07
     for
    0.07
     фен
    0.07
    Distinct
    0.07
    Activations Density 0.003%
    No Known Activations