© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48728
    Prev
    Next
    INDEX
    Explanations

    WWE Hall of Fame

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    മേ
    -0.08
    Vp
    -0.07
    อ่าน
    -0.07
    benz
    -0.07
    گذ
    -0.07
    <c
    -0.07
    ília
    -0.07
     grasp
    -0.07
    iedades
    -0.07
     ув
    -0.07
    POSITIVE LOGITS
    ండ్ర
    0.08
     bedrag
    0.08
    ്യ
    0.08
     hjemme
    0.08
     Aya
    0.07
     Fame
    0.07
    科
    0.07
    urator
    0.07
     éch
    0.07
    ్యత
    0.07
    Activations Density 0.006%

    No Known Activations