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. 112756
    Prev
    Next
    INDEX
    Explanations

    =

    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
     historic
    -0.09
    Histor
    -0.08
     historically
    -0.08
    Packing
    -0.08
    -0.08
     lateral
    -0.08
     Norte
    -0.07
    Goals
    -0.07
    powered
    -0.07
    urb
    -0.07
    POSITIVE LOGITS
     endgült
    0.10
     Hess
    0.10
     বাৰ
    0.09
     nochmals
    0.09
     Ալ
    0.09
     రెండ
    0.08
     dimoun
    0.08
     კვლავ
    0.08
    ddit
    0.08
     ಮತ್ತೆ
    0.08
    Activations Density 0.016%

    No Known Activations