© 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. 24731
    Prev
    Next
    INDEX
    Explanations

    neural network training callbacks

    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
     =",
    -0.08
    ","#
    -0.08
    ứ
    -0.07
    禧
    -0.07
    ")
    -0.07
     syndrome
    -0.07
    شرة
    -0.07
    ypass
    -0.07
    ",↵//
    -0.07
    lyg
    -0.07
    POSITIVE LOGITS
     Result
    0.09
    IMATION
    0.08
    -Be
    0.08
    现实
    0.07
     Approx
    0.07
    .Result
    0.07
    	Result
    0.07
     Visibility
    0.07
     réal
    0.07
     extrap
    0.07
    Activations Density 0.001%

    No Known Activations