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. 24033
    Prev
    Next
    INDEX
    Explanations

    IT and user services

    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
    _money
    -0.09
     beating
    -0.08
     القدم
    -0.08
     sacks
    -0.08
     tern
    -0.08
    _enemy
    -0.08
     الحرب
    -0.08
    _piece
    -0.08
    展开
    -0.08
     billi
    -0.08
    POSITIVE LOGITS
     onboarding
    0.10
     permissions
    0.10
     automated
    0.10
    权限
    0.10
    .Users
    0.10
    LDAP
    0.10
     remediation
    0.09
     users
    0.09
     automation
    0.09
     utilisateurs
    0.09
    Activations Density 0.031%

    No Known Activations