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. 112819
    Prev
    Next
    INDEX
    Explanations

    lunge

    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
    ако
    -0.08
     payload
    -0.08
    Auto
    -0.07
    anko
    -0.07
    apie
    -0.07
     Hym
    -0.07
    背景
    -0.07
     pasti
    -0.07
    ро
    -0.07
    ıb
    -0.07
    POSITIVE LOGITS
     cotidiana
    0.08
     اليومية
    0.08
    跌
    0.08
     ون
    0.08
    hend
    0.08
     dagelijks
    0.08
     sehari
    0.07
     Hampshire
    0.07
     daily
    0.07
     quotidienne
    0.07
    Activations Density 0.000%

    No Known Activations