© 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. 26517
    Prev
    Next
    INDEX
    Explanations

    wrench

    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
    -e
    -0.07
     epit
    -0.07
     epistem
    -0.07
     ਦਰ
    -0.07
    μμ
    -0.07
     दर्श
    -0.07
     연구
    -0.07
     বলা
    -0.07
     teor
    -0.07
    jara
    -0.07
    POSITIVE LOGITS
     segíts
    0.09
     రిలీజ్
    0.08
     tərəfindən
    0.08
     yayı
    0.08
     omhoog
    0.08
     assistance
    0.08
     pomocą
    0.08
    -assisted
    0.08
     saad
    0.08
     zunächst
    0.08
    Activations Density 0.013%

    No Known Activations