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. 29794
    Prev
    Next
    INDEX
    Explanations

    ents

    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
    敬
    -0.08
     pince
    -0.07
    FFF
    -0.07
    �
    -0.07
    ereich
    -0.07
    세
    -0.07
     spez
    -0.07
     voller
    -0.07
     chol
    -0.07
    日の
    -0.07
    POSITIVE LOGITS
     بهذا
    0.08
     азыр
    0.08
     winnen
    0.08
     ಮಾಡಲು
    0.08
     demora
    0.08
    рата
    0.08
     naar
    0.08
     अहिले
    0.08
     Atr
    0.07
    ратор
    0.07
    Activations Density 0.006%

    No Known Activations