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. 52655
    Prev
    Next
    INDEX
    Explanations

    2

    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
     কার্য
    -0.09
    reman
    -0.07
    Param
    -0.07
    (lambda
    -0.07
    Receiver
    -0.07
     контроль
    -0.07
     param
    -0.07
     hect
    -0.07
     tika
    -0.07
    তি
    -0.07
    POSITIVE LOGITS
     numbering
    0.09
     Informat
    0.09
    拍拍
    0.08
    čet
    0.08
     നാല
    0.08
     Gallery
    0.08
     Ug
    0.08
     Essence
    0.08
     രാവ
    0.08
     Format
    0.08
    Activations Density 0.007%

    No Known Activations