© 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. 19-RESID-POST-AA
    11. 18581
    Prev
    Next
    INDEX
    Explanations

    sensory descriptions

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    approve
    -0.08
    (ID
    -0.08
    整数
    -0.08
    友情链接
    -0.08
     kompat
    -0.08
     승인
    -0.07
    .factor
    -0.07
    Approve
    -0.07
     Routing
    -0.07
    优惠
    -0.07
    POSITIVE LOGITS
     vivid
    0.28
    描
    0.26
     vividly
    0.25
     descriptions
    0.24
     evoc
    0.23
     descriptive
    0.23
    描述
    0.23
     sensory
    0.23
     描
    0.22
     वर्ण
    0.22
    Activations Density 0.167%

    No Known Activations