Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98240
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regions
    -0.09
     Removing
    -0.09
    ക്ക
    -0.09
     Origin
    -0.09
     Didn
    -0.09
     Kentucky
    -0.09
     Zwei
    -0.08
     Zus
    -0.08
     Sending
    -0.08
     Receiving
    -0.08
    POSITIVE LOGITS
    -րդ
    0.12
    ஆம்
    0.11
    -ე
    0.11
    લું
    0.10
    -nji
    0.10
    ###
    0.10
    -уми
    0.10
    -ին
    0.09
    شنبه
    0.09
     claus
    0.09
    Activations Density 0.015%

    No Known Activations