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. 60992
    Prev
    Next
    INDEX
    Explanations

    lifting

    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
    蒙
    -0.08
    sonder
    -0.08
    হ
    -0.08
     offenen
    -0.07
    জা
    -0.07
    团队
    -0.07
     team
    -0.07
     besonderen
    -0.07
    ichts
    -0.07
     verste
    -0.07
    POSITIVE LOGITS
     kuka
    0.10
     올라
    0.10
    CHASE
    0.09
    δευ
    0.09
     вверх
    0.09
     μέχρι
    0.08
    ดิ
    0.08
     kubva
    0.08
     nkiri
    0.08
    过程中
    0.08
    Activations Density 0.007%

    No Known Activations