© 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. 103147
    Prev
    Next
    INDEX
    Explanations

    begin

    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
    *:
    -0.11
    *",
    -0.10
    ��
    -0.10
     ?",
    -0.10
    "));
    -0.10
    #",
    -0.09
    "For
    -0.09
    "));
↵
    -0.09
     *
    -0.09
    Japan
    -0.09
    POSITIVE LOGITS
    ичным
    0.10
    െയും
    0.10
    ичной
    0.10
     וח
    0.09
    ाऱ्या
    0.09
    ilean
    0.09
    בלת
    0.09
    েকে
    0.09
     ogé
    0.09
    ाऱ
    0.09
    Activations Density 0.002%

    No Known Activations