© 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. 65492
    Prev
    Next
    INDEX
    Explanations

    suppress

    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
    다운
    -0.08
    -ups
    -0.08
     mailing
    -0.07
    353
    -0.07
    '),
    -0.07
    asha
    -0.07
    lyph
    -0.07
     chid
    -0.07
    -tail
    -0.07
     shipping
    -0.07
    POSITIVE LOGITS
     Influ
    0.08
    elernt
    0.08
     valores
    0.08
     llegando
    0.08
     problém
    0.08
     pasa
    0.08
     опы
    0.08
    בעיה
    0.08
     premios
    0.07
     vrijed
    0.07
    Activations Density 0.001%

    No Known Activations