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. 130887
    Prev
    Next
    INDEX
    Explanations

    after

    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
     Blend
    -0.12
     Leading
    -0.10
     Crop
    -0.10
    blend
    -0.10
     Swap
    -0.09
    -match
    -0.09
     Dive
    -0.09
     Flip
    -0.09
     depleted
    -0.09
     automobile
    -0.09
    POSITIVE LOGITS
     app
    0.14
     adjoining
    0.13
     flooring
    0.13
     squ
    0.12
     replacing
    0.12
     reducing
    0.12
     summ
    0.12
     averaging
    0.11
     changing
    0.11
     substit
    0.11
    Activations Density 0.052%

    No Known Activations