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. 120038
    Prev
    Next
    INDEX
    Explanations

    Nort

    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
     venced
    -0.08
     بر
    -0.08
     gelingt
    -0.08
    Disposition
    -0.08
    (Parser
    -0.08
     dispositions
    -0.08
    chell
    -0.08
     Jar
    -0.08
    ohon
    -0.08
     Crow
    -0.08
    POSITIVE LOGITS
    属于
    0.09
    个人
    0.09
    我是
    0.09
    我的
    0.09
    普通
    0.09
     individuele
    0.09
     belong
    0.09
     firsthand
    0.09
    ,my
    0.08
     pertenec
    0.08
    Activations Density 0.243%

    No Known Activations