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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30894
    Prev
    Next
    INDEX
    Explanations

    regex "g" flag

    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
    .GPIO
    -0.08
    orical
    -0.08
     BSP
    -0.08
    Above
    -0.08
    춤
    -0.08
     biology
    -0.08
    ynthetic
    -0.08
    asured
    -0.07
    Bundles
    -0.07
     buds
    -0.07
    POSITIVE LOGITS
    .horizontal
    0.08
     пораж
    0.08
     Horizontal
    0.08
     удал
    0.08
     פ
    0.07
     протяжении
    0.07
    ременно
    0.07
     Horiz
    0.07
     Entfer
    0.07
    _HORIZONTAL
    0.07
    Activations Density 0.001%

    No Known Activations