© 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. 44883
    Prev
    Next
    INDEX
    Explanations

    true/correct

    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
     drastically
    -0.07
    KP
    -0.07
    update
    -0.07
    .det
    -0.07
     opr
    -0.07
    (cid
    -0.07
     KP
    -0.07
    Z
    -0.07
    <'
    -0.07
    pth
    -0.07
    POSITIVE LOGITS
     ✓
    0.09
    ，因为
    0.09
     certamente
    0.08
     TRUE
    0.08
     celeb
    0.08
     scientifically
    0.08
    认为
    0.08
     factual
    0.08
     صحة
    0.08
     Kutani
    0.08
    Activations Density 0.025%

    No Known Activations