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. 11619
    Prev
    Next
    INDEX
    Explanations

    Horseback riding

    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
    mla
    -0.09
    :]↵↵
    -0.08
     alliances
    -0.07
    bos
    -0.07
    may
    -0.07
    glu
    -0.07
    />
    -0.07
     dopamine
    -0.07
     размера
    -0.07
    bundle
    -0.07
    POSITIVE LOGITS
     horseback
    0.11
     golf
    0.11
     प्रतियोग
    0.10
     क्लब
    0.10
     beginner
    0.09
     randonnée
    0.09
    vereniging
    0.09
     Anfänger
    0.09
    trainer
    0.09
     تدريب
    0.09
    Activations Density 0.006%

    No Known Activations