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. 98161
    Prev
    Next
    INDEX
    Explanations

    sinister, horrifying

    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
    -0.08
    勤
    -0.08
    MAG
    -0.07
    昨天
    -0.07
    /input
    -0.07
    奋斗
    -0.07
     Fighter
    -0.07
    ];//
    -0.07
     Fired
    -0.06
    magan
    -0.06
    POSITIVE LOGITS
     sinister
    0.27
     horrifying
    0.23
     mac
    0.23
     unsettling
    0.23
     horrific
    0.23
     dreadful
    0.22
     creepy
    0.22
     terrifying
    0.21
     omin
    0.21
     grotes
    0.21
    Activations Density 0.074%

    No Known Activations