© 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. 19-RESID-POST-AA
    11. 102628
    Prev
    Next
    INDEX
    Explanations

    turnover

    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
     состояние
    -0.08
     persistent
    -0.08
     duplication
    -0.08
    persistent
    -0.07
    done
    -0.07
     inheritance
    -0.07
     Django
    -0.07
    уляр
    -0.07
     persistence
    -0.07
     repeated
    -0.07
    POSITIVE LOGITS
    率
    0.18
     Rates
    0.17
    율
    0.17
     rates
    0.16
    _rates
    0.16
    _rate
    0.16
    Rate
    0.16
     दर
    0.16
    Rates
    0.16
     Rate
    0.15
    Activations Density 0.011%

    No Known Activations