Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77500
    Prev
    Next
    INDEX
    Explanations

    Colors

    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
    .Filters
    -0.08
     받아
    -0.08
     جات
    -0.08
     minimizar
    -0.08
    ঃ
    -0.07
    /*!
    -0.07
     unión
    -0.07
    ുകള
    -0.07
    _CURRENT
    -0.07
    ынды
    -0.07
    POSITIVE LOGITS
     dragons
    0.09
     dragon
    0.09
     Wolves
    0.08
    Dragon
    0.07
     dwar
    0.07
     देव
    0.07
     पर्व
    0.07
     Night
    0.07
     Dragon
    0.07
     Wine
    0.07
    Activations Density 0.023%

    No Known Activations