© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8193
    Prev
    Next
    INDEX
    Explanations

    cell lines

    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
     laminate
    -0.08
     unang
    -0.08
    ره
    -0.08
     unlocked
    -0.08
    ，全
    -0.08
     நீ
    -0.07
     رقم
    -0.07
    Residential
    -0.07
     оз
    -0.07
     educators
    -0.07
    POSITIVE LOGITS
     Filho
    0.09
     digestion
    0.08
    Nal
    0.08
     vergeben
    0.08
    abbo
    0.08
    프화이트
    0.07
     articolo
    0.07
     doxy
    0.07
     Dialogue
    0.07
    šli
    0.07
    Activations Density 0.001%

    No Known Activations