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. 42204
    Prev
    Next
    INDEX
    Explanations

    ±

    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
    习
    -0.08
     alld
    -0.08
     Tulsa
    -0.08
    習
    -0.08
    ตลาด
    -0.08
     worldwide
    -0.08
    全过程
    -0.08
    �
    -0.08
     urząd
    -0.07
     poch
    -0.07
    POSITIVE LOGITS
    regon
    0.09
    ّة
    0.09
    Depending
    0.08
    Vol
    0.08
     Depending
    0.08
     depending
    0.07
    moz
    0.07
    �
    0.07
     Pain
    0.07
    (-
    0.07
    Activations Density 0.013%

    No Known Activations