© 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. 42998
    Prev
    Next
    INDEX
    Explanations

    tax payments

    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
    indexed
    -0.07
    yper
    -0.07
     Fake
    -0.07
     Checked
    -0.07
    Serv
    -0.07
    Deg
    -0.07
     Jensen
    -0.07
     convex
    -0.07
    jg
    -0.07
    Sr
    -0.07
    POSITIVE LOGITS
     계획
    0.10
     خطة
    0.10
     eingerichtet
    0.10
     plans
    0.09
     kế
    0.09
    计划
    0.08
    }}>
    0.08
     إعداد
    0.08
    ]])
    0.08
     מ
    0.08
    Activations Density 0.005%

    No Known Activations