© 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. 23-RESID-POST-AA
    11. 5935
    Prev
    Next
    INDEX
    Explanations

    quantity

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     दोन
    -0.08
    3
    -0.08
     Two
    -0.08
     Higher
    -0.08
     drei
    -0.08
     sharper
    -0.08
     höheren
    -0.08
     zwei
    -0.08
     قصيرة
    -0.08
     két
    -0.08
    POSITIVE LOGITS
     numerous
    0.42
    大量
    0.42
     lots
    0.41
     countless
    0.41
     many
    0.40
    很多
    0.39
     많은
    0.39
     plenty
    0.39
     viele
    0.38
     الكثير
    0.38
    Activations Density 0.236%

    No Known Activations