© 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. 70031
    Prev
    Next
    INDEX
    Explanations

    Punctuation/Code

    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
    $return
    -0.08
     provisional
    -0.08
    ，此
    -0.07
    Speaker
    -0.07
    VERS
    -0.07
    .answers
    -0.07
     Speaker
    -0.07
    .grad
    -0.07
     speaker
    -0.07
     discuter
    -0.07
    POSITIVE LOGITS
    iculture
    0.09
     действий
    0.08
     junto
    0.08
     Christianity
    0.08
     explosion
    0.08
     Christians
    0.08
     creation
    0.08
     Julian
    0.08
     முன்ன
    0.08
    _creation
    0.08
    Activations Density 0.000%

    No Known Activations