Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 108828
    Prev
    Next
    INDEX
    Explanations

    Prompt

    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
    ونې
    -0.08
    ৃতিক
    -0.08
    pot
    -0.08
    irting
    -0.08
     potentials
    -0.08
    pots
    -0.08
     угроз
    -0.08
     debts
    -0.07
     igjen
    -0.07
    ']")).
    -0.07
    POSITIVE LOGITS
     હશે
    0.10
     હો�
    0.09
    दय
    0.08
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.08
     ખાસ
    0.08
     سيكون
    0.08
     "\\
    0.08
    RT
    0.08
     Fu
    0.07
    _O
    0.07
    Activations Density 0.004%

    No Known Activations