© 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. 31154
    Prev
    Next
    INDEX
    Explanations

    withdraw

    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
    습
    -0.07
     looking
    -0.07
    -0.07
     Eun
    -0.07
    other
    -0.07
    ованию
    -0.07
     elucid
    -0.07
     allá
    -0.07
     Lisa
    -0.06
     elaborate
    -0.06
    POSITIVE LOGITS
    🏼
    0.09
     apologies
    0.08
    cq
    0.08
    rig
    0.08
    Stmt
    0.08
     assent
    0.08
     withdrew
    0.08
    掉
    0.08
     نع
    0.07
     والي
    0.07
    Activations Density 0.008%
    No Known Activations