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. 42892
    Prev
    Next
    INDEX
    Explanations

    Romanian and other languages

    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
     Lol
    -0.08
    maß
    -0.08
    ビ
    -0.07
     Spi
    -0.07
     Cannon
    -0.07
    वी
    -0.07
     Colorado
    -0.07
    aner
    -0.07
     FACE
    -0.07
     Weihnachten
    -0.07
    POSITIVE LOGITS
     everybody
    0.09
    în
    0.09
     спад
    0.09
     kotlin
    0.09
     poate
    0.08
    Catalogue
    0.08
     Kyiv
    0.08
    Centre
    0.08
     atribut
    0.08
     pozn
    0.08
    Activations Density 0.031%

    No Known Activations