© 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. 78159
    Prev
    Next
    INDEX
    Explanations

    speakers and audio

    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
     exempt
    -0.09
    Consent
    -0.09
    .username
    -0.09
    审批
    -0.09
    Swagger
    -0.08
    CRUD
    -0.08
    	username
    -0.08
    行政
    -0.08
    Administrative
    -0.08
    Clinical
    -0.08
    POSITIVE LOGITS
     headphones
    0.12
    woofer
    0.12
     speakers
    0.12
     headphone
    0.12
     acoust
    0.11
     speaker
    0.11
     Acoustic
    0.11
     JBL
    0.11
     acoustic
    0.11
     Outdoor
    0.11
    Activations Density 0.029%

    No Known Activations