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. 131033
    Prev
    Next
    INDEX
    Explanations

    finds

    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
     contend
    -0.08
     PET
    -0.08
     paced
    -0.08
     auparavant
    -0.07
    ))){↵
    -0.07
    .parse
    -0.07
     Malone
    -0.07
     previously
    -0.07
     Davis
    -0.07
     lend
    -0.07
    POSITIVE LOGITS
    aurant
    0.08
    ocrat
    0.08
     ethanol
    0.08
     worthy
    0.08
    Chosen
    0.08
     curta
    0.07
     Worth
    0.07
    Dlg
    0.07
     Natura
    0.07
    રૂપ
    0.07
    Activations Density 0.000%

    No Known Activations