© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 69938
    Prev
    Next
    INDEX
    Explanations

    work

    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
     soulful
    -0.09
     spins
    -0.08
     articol
    -0.08
    單
    -0.08
     rhe
    -0.08
    saus
    -0.07
    ਾਇ
    -0.07
     зв
    -0.07
    谋
    -0.07
     sebe
    -0.07
    POSITIVE LOGITS
    	board
    0.08
    .ret
    0.07
    HAR
    0.07
    	ret
    0.07
    다가
    0.07
     board
    0.07
    Aligned
    0.07
    -tight
    0.07
     deterministic
    0.07
     trú
    0.07
    Activations Density 0.003%

    No Known Activations