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. 129922
    Prev
    Next
    INDEX
    Explanations

    could

    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
    -hole
    -0.08
    tria
    -0.07
    leri
    -0.07
    shay
    -0.07
    enne
    -0.07
     reportedly
    -0.07
    標
    -0.07
    佐
    -0.07
    trica
    -0.07
    hole
    -0.07
    POSITIVE LOGITS
     interpreting
    0.08
     interpreted
    0.08
     superfic
    0.08
     subcon
    0.08
     просто
    0.08
     intending
    0.08
    /**↵
    0.08
    ිත
    0.08
     воспри
    0.08
     interpretação
    0.08
    Activations Density 0.055%

    No Known Activations