© 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. 70232
    Prev
    Next
    INDEX
    Explanations

    ation

    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
    ma
    -0.10
     пот
    -0.08
     turb
    -0.08
     Jupiter
    -0.08
     NASA
    -0.07
    trim
    -0.07
    speed
    -0.07
    gal
    -0.07
    -food
    -0.07
     Tai
    -0.07
    POSITIVE LOGITS
    Words
    0.08
    .words
    0.08
     Elementary
    0.08
     relapse
    0.08
    解除
    0.08
     capitalist
    0.08
     Linden
    0.08
    之一
    0.08
     친구
    0.08
     రిల
    0.08
    Activations Density 0.006%

    No Known Activations