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. 11-RESID-POST-AA
    6. 75892
    Prev
    Next
    INDEX
    Explanations

    sodium and potassium

    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
    tracks
    -0.10
    doch
    -0.09
    fits
    -0.08
    TRACK
    -0.08
    dirty
    -0.08
     surfaced
    -0.08
    track
    -0.07
     shaped
    -0.07
     �
    -0.07
    foundation
    -0.07
    POSITIVE LOGITS
    :G
    0.08
     probleml
    0.08
     pě
    0.08
     cass
    0.08
    .System
    0.08
     chloride
    0.08
     Pale
    0.08
     Kartoff
    0.07
     heads
    0.07
     réactions
    0.07
    Activations Density 0.006%

    No Known Activations