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. 53205
    Prev
    Next
    INDEX
    Explanations

    think

    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
    轴
    -0.07
     gritty
    -0.07
    prü
    -0.07
    Հ
    -0.07
     Prüf
    -0.07
    W
    -0.07
    .rf
    -0.07
    છ
    -0.07
     seamlessly
    -0.07
     prüfen
    -0.07
    POSITIVE LOGITS
     menjal
    0.09
     odam
    0.09
     kot
    0.08
    不错
    0.08
    乎
    0.08
     சே
    0.08
    _ALREADY
    0.08
    年前
    0.08
     intox
    0.08
     danske
    0.08
    Activations Density 0.027%

    No Known Activations