© 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. 5381
    Prev
    Next
    INDEX
    Explanations

    sw

    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
    muje
    -0.09
    rası
    -0.08
    ząc
    -0.08
    pok
    -0.08
     dwa
    -0.08
    nés
    -0.08
     wagers
    -0.08
    vaise
    -0.08
    jach
    -0.08
    乔
    -0.08
    POSITIVE LOGITS
    el
    0.17
    anky
    0.13
    elk
    0.11
    amped
    0.10
    elh
    0.10
    elled
    0.10
    arthy
    0.10
    elha
    0.09
    aying
    0.09
    anning
    0.09
    Activations Density 0.002%

    No Known Activations