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. 78544
    Prev
    Next
    INDEX
    Explanations

    of

    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
     פור
    -0.08
    447
    -0.08
    Export
    -0.08
    ар
    -0.07
     cheaply
    -0.07
     ارسال
    -0.07
     atre
    -0.07
    (fi
    -0.07
     آمده
    -0.07
    ërt
    -0.07
    POSITIVE LOGITS
     জন
    0.08
     regering
    0.08
     乐
    0.08
    .enemy
    0.08
    .handler
    0.07
     enact
    0.07
     vener
    0.07
    ാബ
    0.07
     Stevie
    0.07
    �
    0.07
    Activations Density 0.006%

    No Known Activations