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. 7-RESID-POST-AA
    6. 131069
    Prev
    Next
    INDEX
    Explanations

    cells, glycoproteins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieel
    -0.08
     dictates
    -0.08
     KEEP
    -0.07
    导致
    -0.07
    Retail
    -0.07
     fwy
    -0.07
    یے
    -0.07
     Retail
    -0.07
    拓
    -0.07
     വ്യാപ
    -0.07
    POSITIVE LOGITS
     bumps
    0.09
     describe
    0.07
    value
    0.07
     가치
    0.07
    �
    0.07
     �
    0.07
     bih
    0.07
    'value
    0.07
    .value
    0.07
     protr
    0.07
    Activations Density 0.000%

    No Known Activations