© 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. 8203
    Prev
    Next
    INDEX
    Explanations

    ization

    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
     Witt
    -0.08
    pción
    -0.08
     venom
    -0.08
    XE
    -0.08
    พระ
    -0.07
    깔
    -0.07
    jni
    -0.07
     wł
    -0.07
     pae
    -0.07
    391
    -0.07
    POSITIVE LOGITS
     hinaus
    0.10
     بلکه
    0.09
     إلا
    0.09
     anymore
    0.09
     बल्कि
    0.08
    之外
    0.08
    欲
    0.08
     ahubwo
    0.08
    より
    0.08
     אלא
    0.08
    Activations Density 0.103%

    No Known Activations