© 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. 23-RESID-POST-AA
    11. 50885
    Prev
    Next
    INDEX
    Explanations

    先

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olve
    -0.09
    ième
    -0.09
    olicited
    -0.09
    ional
    -0.09
    ificance
    -0.09
    itative
    -0.08
    -Part
    -0.08
    ified
    -0.08
    ladesh
    -0.08
    inema
    -0.08
    POSITIVE LOGITS
    驱
    0.14
    �
    0.11
    导
    0.11
    贤
    0.10
    遣
    0.10
    烈
    0.10
     driver
    0.10
    �
    0.09
    	driver
    0.09
    例
    0.09
    Activations Density 0.002%

    No Known Activations