© 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. 11-RESID-POST-AA
    11. 75453
    Prev
    Next
    INDEX
    Explanations

    coding errors and references

    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
    Можно
    -0.08
    isis
    -0.08
     Можно
    -0.08
    нал
    -0.08
    sta
    -0.08
    OGR
    -0.08
    STA
    -0.08
    unciation
    -0.08
    ोलन
    -0.08
    øte
    -0.07
    POSITIVE LOGITS
    .provider
    0.09
     mainstream
    0.08
     प्रदान
    0.07
     Arom
    0.07
     arom
    0.07
     atmospheric
    0.07
     mening
    0.07
    aras
    0.07
     benöt
    0.07
     فراہم
    0.07
    Activations Density 0.000%

    No Known Activations