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. 48996
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     mascot
    -0.08
    MV
    -0.08
    玄机
    -0.08
     چاپ
    -0.08
    MVC
    -0.07
    лика
    -0.07
    ানি
    -0.07
     Weighted
    -0.07
     optimiser
    -0.07
     сув
    -0.07
    POSITIVE LOGITS
     intervals
    0.10
     jeweils
    0.09
     periods
    0.09
    周期
    0.09
     perioden
    0.09
     अंतर
    0.08
     interval
    0.08
     cycle
    0.08
     contiguous
    0.08
     berlangsung
    0.08
    Activations Density 0.019%

    No Known Activations