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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 13326
    Prev
    Next
    INDEX
    Explanations

    ±

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upro
    -0.08
    Mic
    -0.08
     প
    -0.08
    Recruit
    -0.08
    টির
    -0.08
    那里
    -0.08
    �
    -0.08
     wield
    -0.08
     অস
    -0.08
    യായി
    -0.07
    POSITIVE LOGITS
     rationale
    0.08
     constraints
    0.08
     lap
    0.07
     manc
    0.07
     formatting
    0.07
     prescribing
    0.07
     bodies
    0.07
    黄
    0.07
     लॉ
    0.07
     الولايات
    0.07
    Activations Density 0.009%

    No Known Activations