© 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. 16480
    Prev
    Next
    INDEX
    Explanations

    os/Rooibos

    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
    正规的
    -0.08
    inə
    -0.08
    ató
    -0.07
    267
    -0.07
    ovic
    -0.07
     largura
    -0.07
    倡
    -0.07
    inction
    -0.07
    inud
    -0.07
    ipherals
    -0.07
    POSITIVE LOGITS
     Tess
    0.09
     rojo
    0.09
     gland
    0.08
     bisexual
    0.08
     trek
    0.08
     warms
    0.08
     Ginger
    0.08
     amarillo
    0.08
    �
    0.08
     modifications
    0.08
    Activations Density 0.003%

    No Known Activations