© 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. 23-RESID-POST-AA
    11. 96181
    Prev
    Next
    INDEX
    Explanations

    Calculations / Russian / Computing

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _over
    -0.09
     över
    -0.08
    anato
    -0.08
     c
    -0.08
    .over
    -0.08
    注文
    -0.08
    \Not
    -0.08
     přes
    -0.08
     bestel
    -0.07
     سفارش
    -0.07
    POSITIVE LOGITS
    asured
    0.08
    loid
    0.07
     es
    0.07
     congressional
    0.07
    REFIX
    0.07
    -host
    0.07
    -prefix
    0.07
    MSC
    0.07
    Wet
    0.07
    onomic
    0.07
    Activations Density 0.017%

    No Known Activations