© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18660
    Prev
    Next
    INDEX
    Explanations

    retirement/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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overturned
    -0.08
     degener
    -0.08
    usa
    -0.08
     verlichting
    -0.08
     erleben
    -0.08
     sensational
    -0.08
    Brightness
    -0.08
     energies
    -0.08
     enumeration
    -0.07
     reopened
    -0.07
    POSITIVE LOGITS
     Einzahlung
    0.19
    缴
    0.16
     contributions
    0.15
     Contributions
    0.14
     payroll
    0.14
     가입
    0.14
     kontrib
    0.14
     yatır
    0.14
     contribuição
    0.14
     bijdrage
    0.13
    Activations Density 0.022%

    No Known Activations