© 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. 3-RESID-POST-AA
    11. 2857
    Prev
    Next
    INDEX
    Explanations

    甘

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grote
    -0.09
    geno
    -0.09
    GES
    -0.08
     ning
    -0.08
    Genero
    -0.08
     thym
    -0.08
    TOK
    -0.07
     GE
    -0.07
     ratione
    -0.07
     tanta
    -0.07
    POSITIVE LOGITS
    vir
    0.08
     vir
    0.08
     discontinu
    0.08
     ا
    0.07
    hyd
    0.07
     hat
    0.07
    ลา
    0.07
     box
    0.07
    വർ
    0.07
    స
    0.07
    Activations Density 0.001%

    No Known Activations