© 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. 78250
    Prev
    Next
    INDEX
    Explanations

    Pod

    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
     Wald
    -0.09
    ron
    -0.08
    alde
    -0.08
    naire
    -0.08
     compulsory
    -0.08
     প্রতিষ্ঠান
    -0.08
     Airports
    -0.08
    额
    -0.07
    rons
    -0.07
    roke
    -0.07
    POSITIVE LOGITS
     संगीत
    0.09
    .music
    0.09
     musical
    0.08
     musica
    0.08
     music
    0.08
     música
    0.08
     Melody
    0.08
    留言
    0.08
     Dreams
    0.08
     drums
    0.07
    Activations Density 0.002%

    No Known Activations