© 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. 3-RESID-POST-AA
    11. 1368
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     controversies
    -0.08
    Pok
    -0.08
     шә
    -0.08
     reactions
    -0.08
     polém
    -0.08
    会
    -0.07
     Accommodation
    -0.07
     perros
    -0.07
     Cont
    -0.07
     श्रद्ध
    -0.07
    POSITIVE LOGITS
     पत
    0.08
    von
    0.07
     HV
    0.07
     von
    0.07
    .JSON
    0.07
     PROC
    0.07
    /item
    0.07
    (item
    0.07
    gnu
    0.07
     alas
    0.07
    Activations Density 0.001%

    No Known Activations