© 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. 23-RESID-POST-AA
    11. 49414
    Prev
    Next
    INDEX
    Explanations

    size comparison

    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
     deep
    -0.12
     more
    -0.11
    更多
    -0.11
    deep
    -0.10
    More
    -0.10
    Deep
    -0.10
     low
    -0.10
     high
    -0.10
    more
    -0.09
    high
    -0.09
    POSITIVE LOGITS
     larger
    0.32
     smaller
    0.31
     Larger
    0.31
     Smaller
    0.29
     größeren
    0.26
     größere
    0.25
    larg
    0.24
     kleinere
    0.24
     grotere
    0.24
     größer
    0.24
    Activations Density 0.106%

    No Known Activations