© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29518
    Prev
    Next
    INDEX
    Explanations

    要求

    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
     Gör
    -0.08
     concr
    -0.08
     liebe
    -0.08
     concierge
    -0.08
    ்ப்பு
    -0.08
     வி�
    -0.07
     TED
    -0.07
     tän
    -0.07
    (byte
    -0.07
     뛰
    -0.07
    POSITIVE LOGITS
    Exclude
    0.09
    禁止
    0.09
     prohibited
    0.08
     mandated
    0.08
     prohibits
    0.08
    Excluded
    0.08
     presumably
    0.08
     prohibition
    0.08
     exclusions
    0.08
    /legal
    0.07
    Activations Density 0.001%

    No Known Activations