© 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. 7-RESID-POST-AA
    11. 1457
    Prev
    Next
    INDEX
    Explanations

    wali

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dieting
    -0.09
     grapple
    -0.08
    .Month
    -0.08
    -0.08
    ıy
    -0.08
    .Nav
    -0.08
     bestimm
    -0.08
    .MONTH
    -0.08
    Maintenance
    -0.08
     onderhouden
    -0.08
    POSITIVE LOGITS
     kay
    0.09
     brilliance
    0.08
     vào
    0.08
    lite
    0.08
     त
    0.08
     Vil
    0.07
     ത
    0.07
    宇
    0.07
     വിദ്യ
    0.07
    	cs
    0.07
    Activations Density 0.005%
    No Known Activations