Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 76027
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    teen
    -0.07
    anim
    -0.07
     tequila
    -0.07
     ():
    -0.07
     hospital
    -0.07
     mag
    -0.07
    ().↵
    -0.07
     camel
    -0.07
     cod
    -0.07
    (cam
    -0.07
    POSITIVE LOGITS
     сұ
    0.09
     αυτή
    0.08
     Brooks
    0.08
     unlocked
    0.08
     pār
    0.08
     पैदा
    0.08
    orris
    0.08
    ിയാണ്
    0.08
     срод
    0.08
     скорость
    0.08
    Activations Density 0.035%

    No Known Activations