© 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. 68049
    Prev
    Next
    INDEX
    Explanations

    mood

    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
     কোনও
    -0.08
     মিল
    -0.08
    curr
    -0.08
     mil
    -0.08
    iper
    -0.07
    เอง
    -0.07
     নিজ
    -0.07
    458
    -0.07
     বিরুদ্ধে
    -0.07
    Eligibility
    -0.07
    POSITIVE LOGITS
     शैली
    0.09
    Vintage
    0.09
     festive
    0.09
    寓
    0.08
    �
    0.08
     प्रस्त
    0.08
     portrayal
    0.08
    /icon
    0.08
     hæ
    0.08
     风
    0.08
    Activations Density 0.004%

    No Known Activations