© 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. 23-RESID-POST-AA
    11. 50144
    Prev
    Next
    INDEX
    Explanations

    retirement and pension

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FAFSA
    -0.08
    .family
    -0.08
    esterol
    -0.08
     cousin
    -0.08
    partum
    -0.08
     가족
    -0.08
     cousins
    -0.08
     familiale
    -0.08
     পরিবারের
    -0.08
     الأسرة
    -0.08
    POSITIVE LOGITS
    defined
    0.14
     defined
    0.14
     Defined
    0.14
    Defined
    0.14
     പെ
    0.12
     ஓ
    0.12
     ನಿವ
    0.11
     വിര
    0.11
    p
    0.10
     definida
    0.10
    Activations Density 0.014%

    No Known Activations