© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103539
    Prev
    Next
    INDEX
    Explanations

    ic

    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
    uschen
    -0.09
     misma
    -0.08
     spieg
    -0.08
    즘
    -0.08
     bestätigen
    -0.08
     estrategias
    -0.08
     mismos
    -0.08
     estrategia
    -0.08
     kug
    -0.08
     strikt
    -0.08
    POSITIVE LOGITS
     alliances
    0.13
     alliance
    0.11
     partnerships
    0.11
     Partnerships
    0.11
     Alli
    0.11
     напрям
    0.10
     importance
    0.10
     Planning
    0.10
    znym
    0.09
    znych
    0.09
    Activations Density 0.005%

    No Known Activations