© 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. 15-RESID-POST-AA
    11. 16287
    Prev
    Next
    INDEX
    Explanations

    finds telegram bot API tokens

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Raceway
    -0.08
    ーダ
    -0.08
    endeu
    -0.08
     dinâmica
    -0.08
    动态图
    -0.08
    送料
    -0.07
    edka
    -0.07
     الساخ
    -0.07
    旬
    -0.07
     sólidos
    -0.07
    POSITIVE LOGITS
    חה
    0.08
     wiadomo
    0.08
    (...
    0.08
    ((-
    0.08
    0.08
    -ie
    0.07
    cler
    0.07
    XE
    0.07
    clerosis
    0.07
    ([...
    0.07
    Activations Density 0.002%
    No Known Activations