© 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. 102621
    Prev
    Next
    INDEX
    Explanations

    Non-English language

    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
     in
    -0.08
     (
    -0.08
     கே
    -0.07
     with
    -0.07
    150
    -0.07
     that
    -0.07
     represent
    -0.07
    128
    -0.07
    100
    -0.07
     is
    -0.07
    POSITIVE LOGITS
     لابد
    0.10
    ১�
    0.10
    四六
    0.10
    өв
    0.09
     eriti
    0.09
    ահով
    0.09
    ್ನಾಟಕ
    0.09
    өөд
    0.09
     частности
    0.09
    三分彩
    0.09
    Activations Density 0.081%

    No Known Activations