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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114238
    Prev
    Next
    INDEX
    Explanations

    bit

    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
     attributable
    -0.08
    'exploitation
    -0.08
    方面
    -0.08
     aspek
    -0.07
     leurs
    -0.07
    戰
    -0.07
     favour
    -0.07
     controll
    -0.07
     shook
    -0.07
    ’exploitation
    -0.07
    POSITIVE LOGITS
    -sized
    0.08
    目录
    0.08
     гар
    0.08
    LEN
    0.08
    Sized
    0.08
    -size
    0.08
     sized
    0.08
     UIBar
    0.07
     escolares
    0.07
    -uppercase
    0.07
    Activations Density 0.005%

    No Known Activations