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. 113820
    Prev
    Next
    INDEX
    Explanations

    IK

    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
    แห่ง
    -0.07
     prer
    -0.07
     proceedings
    -0.07
     accueill
    -0.07
     costes
    -0.07
     näh
    -0.07
     expenditure
    -0.07
     sow
    -0.07
     customary
    -0.07
     premiers
    -0.07
    POSITIVE LOGITS
    -solving
    0.09
    oci
    0.08
     preocupar
    0.08
     penc
    0.08
    Padding
    0.08
     perfe
    0.08
    zähl
    0.08
    യോഗ
    0.08
     Bela
    0.08
     aching
    0.08
    Activations Density 0.001%

    No Known Activations