© 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. 23-RESID-POST-AA
    11. 50453
    Prev
    Next
    INDEX
    Explanations

    56

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ાઇટ
    -0.09
    ाइट
    -0.08
    iterr
    -0.08
     पेश
    -0.08
    aaaa
    -0.07
     explanations
    -0.07
    aita
    -0.07
    тим
    -0.07
    acific
    -0.07
     Suppliers
    -0.07
    POSITIVE LOGITS
    56
    0.09
    Handshake
    0.08
    ויב
    0.08
    144
    0.08
     התמ
    0.08
     Glue
    0.08
     ولد
    0.08
     kres
    0.08
     upl
    0.08
    تمر
    0.07
    Activations Density 0.002%

    No Known Activations