© 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. 54570
    Prev
    Next
    INDEX
    Explanations

    {

    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
     diesmal
    -0.08
    stedt
    -0.08
     Hof
    -0.07
     Puig
    -0.07
     sonunda
    -0.07
     Silber
    -0.07
    bellion
    -0.07
    ונד
    -0.07
     tarif
    -0.07
     wider
    -0.07
    POSITIVE LOGITS
    盘
    0.08
     ಚೆ
    0.08
     ;
↵
↵
    0.08
    bb
    0.08
    bp
    0.08
     empreg
    0.08
     ;
↵
    0.07
    0.07
    xbe
    0.07
    PSC
    0.07
    Activations Density 0.004%

    No Known Activations