Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30020
    Prev
    Next
    INDEX
    Explanations

    savings

    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
    ń
    -0.08
     staffing
    -0.07
    ต่
    -0.07
    llä
    -0.07
    šta
    -0.07
    wv
    -0.07
     HAV
    -0.07
    plug
    -0.07
     commerciële
    -0.07
     textual
    -0.07
    POSITIVE LOGITS
     motel
    0.09
    恐縮です
    0.09
    قراء
    0.08
     পাঠ
    0.08
    идан
    0.08
     bankroll
    0.08
     supplemented
    0.08
     reisen
    0.08
     لإن
    0.08
    来自
    0.08
    Activations Density 0.022%

    No Known Activations