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. 58937
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     NB
    -0.07
    onje
    -0.07
     variants
    -0.07
     možnosti
    -0.07
     mikt
    -0.07
    cente
    -0.07
     alloy
    -0.07
     কাউ
    -0.07
     количества
    -0.07
    לח
    -0.07
    POSITIVE LOGITS
     Oft
    0.09
    ("/")
    0.08
    +"/"+
    0.08
    .Bool
    0.08
    )||
    0.08
    _AUT
    0.08
    _irq
    0.08
     Junge
    0.08
    zis
    0.07
    JNI
    0.07
    Activations Density 0.047%

    No Known Activations