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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88191
    Prev
    Next
    INDEX
    Explanations

    infinity

    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
    <Model
    -0.08
     foregoing
    -0.08
    rii
    -0.08
     erfolgt
    -0.07
    上述
    -0.07
    inan
    -0.07
     mor
    -0.07
     mí
    -0.07
    estial
    -0.07
     fordel
    -0.07
    POSITIVE LOGITS
     Haha
    0.08
     പോയ
    0.08
     CHF
    0.08
    ನು
    0.08
    thique
    0.07
    outed
    0.07
    खे
    0.07
    werden
    0.07
    兽
    0.07
     geladen
    0.07
    Activations Density 0.001%

    No Known Activations