© 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 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. 112699
    Prev
    Next
    INDEX
    Explanations

    Quotation mark

    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
    esh
    -0.08
     nets
    -0.08
    Ä
    -0.08
    _feats
    -0.08
     kokon
    -0.07
     batting
    -0.07
     Municipal
    -0.07
     TInt
    -0.07
    Locker
    -0.07
     Fest
    -0.07
    POSITIVE LOGITS
     ओर
    0.08
     данный
    0.08
    ordam
    0.07
     shaq
    0.07
     spine
    0.07
     grooves
    0.07
     brunette
    0.07
     प्लेट
    0.07
    จีน
    0.07
     beard
    0.07
    Activations Density 0.002%

    No Known Activations