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. 102930
    Prev
    Next
    INDEX
    Explanations

    opposite

    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
    -mediated
    -0.08
    etha
    -0.08
    steady
    -0.07
    ative
    -0.07
     infusion
    -0.07
     PREFIX
    -0.07
    studio
    -0.07
    ammelt
    -0.07
     Huss
    -0.07
    PREFIX
    -0.07
    POSITIVE LOGITS
    弟
    0.08
    距
    0.08
     Odd
    0.08
     olunan
    0.08
     ital
    0.08
     keluar
    0.08
     '..
    0.08
     apost
    0.08
     ozna
    0.08
     Bene
    0.08
    Activations Density 0.006%

    No Known Activations