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. 106065
    Prev
    Next
    INDEX
    Explanations

    rewrite

    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
     braid
    -0.08
    及时
    -0.08
     wijs
    -0.07
     wedge
    -0.07
     cierre
    -0.07
     đoàn
    -0.07
    otheli
    -0.07
     Clifford
    -0.07
     buckle
    -0.07
     wires
    -0.07
    POSITIVE LOGITS
    omm
    0.08
     рол
    0.08
     �
    0.08
     ак
    0.08
     дня
    0.08
     ав
    0.08
     légèrement
    0.08
     urbana
    0.08
     без
    0.08
    uild
    0.08
    Activations Density 0.012%

    No Known Activations