© 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. 111214
    Prev
    Next
    INDEX
    Explanations

    forest

    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
    'ing
    -0.08
     mor
    -0.08
    tet
    -0.08
     evaluate
    -0.07
     fronter
    -0.07
    MENTS
    -0.07
     elect
    -0.07
    ēji
    -0.07
     бак
    -0.07
    ’ing
    -0.07
    POSITIVE LOGITS
    里的
    0.10
    -grown
    0.08
    暮
    0.08
     rainforest
    0.08
    �
    0.08
    举行
    0.08
    �
    0.08
    中的
    0.08
     carn
    0.07
    /gen
    0.07
    Activations Density 0.013%

    No Known Activations