© 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. 108625
    Prev
    Next
    INDEX
    Explanations

    ack crack

    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
    -sama
    -0.08
     cit
    -0.08
     అభ
    -0.08
     Classified
    -0.07
     malé
    -0.07
     Serg
    -0.07
    jeti
    -0.07
     Nid
    -0.07
     Kabupaten
    -0.07
     inci
    -0.07
    POSITIVE LOGITS
     autumn
    0.08
     cracked
    0.08
     fer
    0.08
     britt
    0.08
    秋
    0.08
     النار
    0.08
     مج
    0.07
     Hollywood
    0.07
     holes
    0.07
     зрения
    0.07
    Activations Density 0.009%

    No Known Activations