© 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. 64672
    Prev
    Next
    INDEX
    Explanations

    numbers around 50

    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
     liquidity
    -0.10
     revenue
    -0.08
     GDP
    -0.08
     درآمد
    -0.08
    GDP
    -0.08
     지급
    -0.08
     integ
    -0.08
     버
    -0.08
     pooling
    -0.07
     transactions
    -0.07
    POSITIVE LOGITS
     angle
    0.11
     angles
    0.10
     Angle
    0.09
    Angle
    0.09
    _angle
    0.09
     approximately
    0.09
    °↵
    0.09
    (angle
    0.09
    °
    0.09
    .angle
    0.08
    Activations Density 0.015%

    No Known Activations