© 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. 129483
    Prev
    Next
    INDEX
    Explanations

    argue

    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
     popularly
    -0.08
     genoemde
    -0.08
     mentioned
    -0.08
    quently
    -0.08
     tenta
    -0.07
     genannten
    -0.07
    (period
    -0.07
     hm
    -0.07
     engem
    -0.07
     costuma
    -0.07
    POSITIVE LOGITS
    此次
    0.08
     zwar
    0.08
     byť
    0.07
     Memb
    0.07
    าถ
    0.07
     необходимость
    0.07
     seien
    0.07
     "'
    0.07
     Jr
    0.07
    _COUNTER
    0.07
    Activations Density 0.102%

    No Known Activations