Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8641
    Prev
    Next
    INDEX
    Explanations

    just

    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
    abee
    -0.08
     ಮಾತ್ರ
    -0.07
    đen
    -0.07
     सुझ
    -0.07
     비롯
    -0.07
    海
    -0.07
    }`);↵
    -0.07
     tanning
    -0.07
     б
    -0.07
    esthetic
    -0.07
    POSITIVE LOGITS
     Southeastern
    0.08
     eso
    0.08
     wahi
    0.08
     etabl
    0.08
     Calif
    0.08
     Mahar
    0.07
     refers
    0.07
     Arn
    0.07
     ikh
    0.07
     Cof
    0.07
    Activations Density 0.023%

    No Known Activations