© 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. 54576
    Prev
    Next
    INDEX
    Explanations

    BIO

    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
     pumpkins
    -0.09
     dormant
    -0.08
     investors
    -0.08
     flexibility
    -0.07
     connections
    -0.07
     customers
    -0.07
    984
    -0.07
    .Gson
    -0.07
     galleries
    -0.07
    iviteit
    -0.07
    POSITIVE LOGITS
    串一
    0.09
    -fashion
    0.09
     পো
    0.09
    lios
    0.09
     acorde
    0.09
     حالت
    0.08
     començar
    0.08
     acord
    0.08
    -fit
    0.08
    דרך
    0.08
    Activations Density 0.001%

    No Known Activations