Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27207
    Prev
    Next
    INDEX
    Explanations

    twist

    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
     পাব
    -0.08
     عمومی
    -0.08
     هڪ
    -0.08
     منش
    -0.08
    一种
    -0.08
    ({↵↵
    -0.07
     ಮೂಲ
    -0.07
     građ
    -0.07
    ({↵//
    -0.07
     rir
    -0.07
    POSITIVE LOGITS
     등장
    0.09
    发生
    0.08
     culminating
    0.08
     reprim
    0.08
    δό
    0.08
     Wester
    0.08
    �
    0.07
     Lost
    0.07
     появляются
    0.07
     Staff
    0.07
    Activations Density 0.049%

    No Known Activations