© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29625
    Prev
    Next
    INDEX
    Explanations

    Grabbing/Holding

    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
     mailing
    -0.08
    VE
    -0.07
     boiling
    -0.07
     Depression
    -0.07
    Voting
    -0.07
     depression
    -0.07
    ٹنگ
    -0.07
    ובה
    -0.07
    úr
    -0.07
    Deprecated
    -0.07
    POSITIVE LOGITS
     Herbal
    0.09
     herbal
    0.09
     addons
    0.09
     eyi
    0.08
    kii
    0.08
     haa
    0.08
    kre
    0.08
    eyo
    0.08
     الذات
    0.08
    alami
    0.08
    Activations Density 0.001%

    No Known Activations