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. 58806
    Prev
    Next
    INDEX
    Explanations

    taxi

    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
     നിറ
    -0.08
    hatikan
    -0.07
    arning
    -0.07
     degener
    -0.07
     توق
    -0.07
     looph
    -0.07
     CLI
    -0.07
    aneous
    -0.07
    βά
    -0.07
     enjoyment
    -0.07
    POSITIVE LOGITS
     traslado
    0.08
     liaison
    0.08
     puente
    0.08
     menuju
    0.08
     લઈ
    0.08
     dur
    0.08
     ||
    0.08
    ipelines
    0.08
    ియర్
    0.07
     Locate
    0.07
    Activations Density 0.013%

    No Known Activations