© 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. 78300
    Prev
    Next
    INDEX
    Explanations

    why

    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
     realidad
    -0.08
    iose
    -0.07
    owej
    -0.07
    enta
    -0.07
    ética
    -0.07
     investing
    -0.07
    _↵↵
    -0.07
    !”
    -0.07
    902
    -0.07
     anyone
    -0.07
    POSITIVE LOGITS
     discour
    0.09
     भ्रम
    0.09
     Qualification
    0.09
     discourage
    0.09
     misunderstanding
    0.09
     qualification
    0.08
     problematic
    0.08
     болуы
    0.08
     болмай
    0.08
     Why
    0.08
    Activations Density 0.022%

    No Known Activations