Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1718
    Prev
    Next
    INDEX
    Explanations

    approach

    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
     bur
    -0.08
     leaning
    -0.08
     Harvey
    -0.08
     folks
    -0.07
     ça
    -0.07
     marinade
    -0.07
     Lynn
    -0.07
     Brewer
    -0.07
    Whole
    -0.07
    politik
    -0.07
    POSITIVE LOGITS
     resemble
    0.08
    Zen
    0.08
     нему
    0.08
     אליו
    0.08
     IAS
    0.08
    engr
    0.08
     specifications
    0.08
     المث
    0.08
     Zen
    0.07
     specs
    0.07
    Activations Density 0.012%

    No Known Activations