© 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 EvalsExportsAPI 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. 69445
    Prev
    Next
    INDEX
    Explanations

    750

    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
    ப்ப
    -0.08
     Charlie
    -0.07
    λη
    -0.07
     responsible
    -0.07
     residue
    -0.07
    +"'
    -0.07
     fom
    -0.07
    aats
    -0.07
    _RELEASE
    -0.07
    CTIONS
    -0.07
    POSITIVE LOGITS
     또한
    0.10
     verið
    0.10
     yfir
    0.09
     친구
    0.09
     また
    0.09
     특히
    0.09
     여기
    0.08
     또는
    0.08
     amis
    0.08
     호
    0.08
    Activations Density 0.008%

    No Known Activations