© 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. 23-RESID-POST-AA
    11. 5900
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Karten
    -0.08
     bevorzug
    -0.08
     privilégi
    -0.08
    MIN
    -0.08
     摄
    -0.08
     privil
    -0.08
     salg
    -0.07
    扑
    -0.07
    TERY
    -0.07
    Privileges
    -0.07
    POSITIVE LOGITS
    gaz
    0.08
    biz
    0.08
     moeten
    0.08
    (OP
    0.08
    بعد
    0.08
    (effect
    0.08
    (view
    0.08
     gw
    0.08
    *r
    0.08
     portfolio
    0.08
    Activations Density 0.001%

    No Known Activations