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. 98307
    Prev
    Next
    INDEX
    Explanations

    Geographic locations

    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
    paused
    -0.08
    ่น
    -0.08
    md
    -0.08
     sportif
    -0.08
    された
    -0.07
    ition
    -0.07
    طع
    -0.07
    itness
    -0.07
    .over
    -0.07
    EDD
    -0.07
    POSITIVE LOGITS
     oceans
    0.10
     River
    0.10
    瓶
    0.09
     Ocean
    0.09
     оке
    0.09
     моря
    0.09
     Valley
    0.09
    河
    0.09
     Azul
    0.09
     Sea
    0.09
    Activations Density 0.057%

    No Known Activations