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. 117752
    Prev
    Next
    INDEX
    Explanations

    fire

    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
    fortune
    -0.09
     affectionate
    -0.09
    Jugador
    -0.08
    Pokemon
    -0.08
     Pokemon
    -0.08
     sehingga
    -0.08
     émotion
    -0.08
     Fragment
    -0.08
    čkih
    -0.08
     الدولار
    -0.08
    POSITIVE LOGITS
    消防
    0.12
     firefighters
    0.10
     fire
    0.09
    救
    0.09
     firefighter
    0.09
     пожар
    0.09
    .prevent
    0.09
    报警
    0.08
     alarms
    0.08
    保障
    0.08
    Activations Density 0.014%

    No Known Activations