© 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. 525
    Prev
    Next
    INDEX
    Explanations

    y

    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
     공동
    -0.08
     Mecklenburg
    -0.08
    宽
    -0.08
    -semibold
    -0.08
    征
    -0.08
     মাস
    -0.08
    _authenticated
    -0.08
    多人
    -0.08
     Motorr
    -0.07
    竞技
    -0.07
    POSITIVE LOGITS
     presents
    0.08
     hemisphere
    0.07
     artificial
    0.07
     kalan
    0.07
     regulates
    0.07
    blank
    0.07
     instead
    0.07
    -pres
    0.07
    amira
    0.07
    Ae
    0.07
    Activations Density 0.009%

    No Known Activations