© 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. 69054
    Prev
    Next
    INDEX
    Explanations

    poverty

    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
    <
    -0.09
    =
    -0.07
     cerc
    -0.07
    .diff
    -0.07
     permettre
    -0.07
     diff
    -0.07
     diferente
    -0.07
     phong
    -0.07
    ophagus
    -0.07
     sentido
    -0.07
    POSITIVE LOGITS
    timeouts
    0.09
    …。
    0.08
     homelessness
    0.08
     الاجتماعية
    0.08
     соці
    0.08
    utches
    0.08
     pobreza
    0.08
     aufmerksam
    0.08
      
↵
↵
    0.08
     социальной
    0.08
    Activations Density 0.010%

    No Known Activations