© 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. 108373
    Prev
    Next
    INDEX
    Explanations

    Qilin

    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
     telefono
    -0.09
     debt
    -0.09
     subsidy
    -0.09
    .Black
    -0.08
    _UNKNOWN
    -0.08
     episod
    -0.08
    Telefono
    -0.08
    ønd
    -0.08
     noct
    -0.07
    dere
    -0.07
    POSITIVE LOGITS
     engraved
    0.08
    ंगा
    0.08
    .baomidou
    0.08
     Lang
    0.08
     चिन
    0.08
    祥云
    0.07
    ‘
    0.07
     yarn
    0.07
    gev
    0.07
    raft
    0.07
    Activations Density 0.003%

    No Known Activations