© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44625
    Prev
    Next
    INDEX
    Explanations

    network communication replies

    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
     worthwhile
    -0.08
    ellington
    -0.07
    -span
    -0.07
    partment
    -0.07
     harness
    -0.07
    &aacute
    -0.07
     Pal
    -0.07
     Compared
    -0.07
    //=
    -0.07
     downtown
    -0.07
    POSITIVE LOGITS
    回应
    0.16
    返信
    0.14
    回复
    0.13
    响应
    0.13
    	reply
    0.12
     भेज
    0.12
     संदेश
    0.12
    .reply
    0.12
     reply
    0.12
     responses
    0.12
    Activations Density 0.010%

    No Known Activations