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. 102981
    Prev
    Next
    INDEX
    Explanations

    tick

    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
     eggs
    -0.08
     succumb
    -0.08
    途
    -0.08
    ם
    -0.08
     telur
    -0.08
     Egg
    -0.07
     intertwined
    -0.07
    wij
    -0.07
     mad
    -0.07
     Preg
    -0.07
    POSITIVE LOGITS
    �
    0.09
    一下
    0.08
     halls
    0.07
    ите
    0.07
    �
    0.07
    /key
    0.07
    -scal
    0.07
     فوق
    0.07
     inspected
    0.07
     связи
    0.07
    Activations Density 0.003%

    No Known Activations