© 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. 96482
    Prev
    Next
    INDEX
    Explanations

    -

    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
     PX
    -0.09
     Turf
    -0.08
     famílias
    -0.08
     وم
    -0.08
    ecture
    -0.08
     pamilya
    -0.08
     Татар
    -0.07
     Поль
    -0.07
    onnas
    -0.07
     ·
    -0.07
    POSITIVE LOGITS
     cheek
    0.10
    _che
    0.09
    Che
    0.08
     nodo
    0.08
     crecimiento
    0.08
    -growth
    0.08
     afront
    0.08
    节点
    0.08
    nią
    0.08
    arit
    0.08
    Activations Density 0.000%

    No Known Activations