© 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. 108612
    Prev
    Next
    INDEX
    Explanations

    triple

    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
     futur
    -0.08
    Notas
    -0.08
    _SCOPE
    -0.08
    Nossa
    -0.07
    和
    -0.07
     stellen
    -0.07
    [`
    -0.07
    ថ
    -0.07
     Senhora
    -0.07
    Bio
    -0.07
    POSITIVE LOGITS
     triples
    0.08
     integer
    0.08
     divisible
    0.08
     recognizable
    0.08
     dhan
    0.08
     illustrative
    0.08
     nối
    0.08
     tidy
    0.08
     traditionnel
    0.07
     rectangle
    0.07
    Activations Density 0.006%

    No Known Activations