© 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. 29628
    Prev
    Next
    INDEX
    Explanations

    Field

    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
     famously
    -0.08
     проверки
    -0.08
    ుద
    -0.08
     reminding
    -0.08
     erinnern
    -0.08
     towering
    -0.07
     famous
    -0.07
     التي
    -0.07
    崎
    -0.07
     seemingly
    -0.07
    POSITIVE LOGITS
     Valencia
    0.08
     nors
    0.07
     Notre
    0.07
    PV
    0.07
    q
    0.07
     �
    0.07
    BUT
    0.07
    'avais
    0.07
    since
    0.07
     tob
    0.07
    Activations Density 0.001%

    No Known Activations