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. 27459
    Prev
    Next
    INDEX
    Explanations

    asks

    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
    ulah
    -0.08
     уда
    -0.07
    ೇವ
    -0.07
    乾
    -0.07
     тебя
    -0.07
     marketers
    -0.07
     зав
    -0.07
    graded
    -0.07
     싸
    -0.07
     thou
    -0.07
    POSITIVE LOGITS
    关于
    0.09
     pinpoint
    0.09
     Acres
    0.08
     درباره
    0.08
     Wiz
    0.07
     Premiere
    0.07
     relating
    0.07
     Lori
    0.07
     vogue
    0.07
     Weiterbildung
    0.07
    Activations Density 0.024%

    No Known Activations