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. 54477
    Prev
    Next
    INDEX
    Explanations

    Middle

    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
    Dose
    -0.08
    ANC
    -0.07
     Fug
    -0.07
     Kendall
    -0.07
     entscheiden
    -0.07
     satur
    -0.07
    判
    -0.07
     康
    -0.07
     quen
    -0.07
    .selection
    -0.07
    POSITIVE LOGITS
     અર
    0.08
    	dst
    0.08
     كى
    0.08
     oliva
    0.08
    orical
    0.08
    ‏
    0.08
     Pakistani
    0.07
    country
    0.07
     Persian
    0.07
     Trom
    0.07
    Activations Density 0.035%

    No Known Activations