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. 111588
    Prev
    Next
    INDEX
    Explanations

    Code and math

    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
     Cos
    -0.08
     oat
    -0.07
     bal
    -0.07
    ീ
    -0.07
     Token
    -0.07
     togg
    -0.07
     Meal
    -0.07
     cos
    -0.07
     Aspect
    -0.07
     caros
    -0.07
    POSITIVE LOGITS
    online
    0.09
     ornament
    0.08
    ام
    0.08
    ancial
    0.08
    オンライン
    0.08
     impec
    0.08
     آنلاین
    0.08
    hini
    0.08
    ออนไลน์
    0.08
    _online
    0.07
    Activations Density 0.000%

    No Known Activations