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. 98610
    Prev
    Next
    INDEX
    Explanations

    change or transform

    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
     removal
    -0.09
     removed
    -0.09
     제거
    -0.09
     Remove
    -0.09
     Removal
    -0.08
     ruined
    -0.08
     إزالة
    -0.08
     odstr
    -0.08
     удалить
    -0.08
     ruining
    -0.08
    POSITIVE LOGITS
     morph
    0.20
     evolves
    0.18
     evolve
    0.17
     undergo
    0.16
     metam
    0.16
    Morph
    0.16
     gains
    0.16
     gaining
    0.15
    變
    0.15
     burge
    0.15
    Activations Density 0.084%

    No Known Activations