© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 44283
    Prev
    Next
    INDEX
    Explanations

    partitions

    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
    .NORTH
    -0.09
    -weather
    -0.08
     lycée
    -0.08
     nhanh
    -0.08
     pupils
    -0.08
    _UART
    -0.08
    .Lerp
    -0.08
     photoc
    -0.08
    MAR
    -0.08
     FEST
    -0.08
    POSITIVE LOGITS
    Sum
    0.08
    ≥
    0.08
    oyal
    0.08
     Sum
    0.08
    _sum
    0.08
     sum
    0.07
     positivity
    0.07
     tamaños
    0.07
     iter
    0.07
    Sizes
    0.07
    Activations Density 0.027%

    No Known Activations