© 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. 54395
    Prev
    Next
    INDEX
    Explanations

    ac

    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
    宗
    -0.08
    -0.07
    arsa
    -0.07
    ાડી
    -0.07
     puzzle
    -0.07
    bij
    -0.07
    jez
    -0.07
    ้
    -0.07
    ्ण
    -0.07
     pledge
    -0.07
    POSITIVE LOGITS
    .Final
    0.08
     Viv
    0.08
     Avant
    0.08
     Rider
    0.07
    oyote
    0.07
    Bands
    0.07
     девуш
    0.07
    ABI
    0.07
     ښځ
    0.07
     hazırl
    0.07
    Activations Density 0.001%

    No Known Activations