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. 26875
    Prev
    Next
    INDEX
    Explanations

    gl

    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
     πλα
    -0.08
    uncate
    -0.08
    _functions
    -0.08
    essages
    -0.08
    跌
    -0.07
    품
    -0.07
    /msg
    -0.07
    imbabwe
    -0.07
     зид
    -0.07
    Funcs
    -0.07
    POSITIVE LOGITS
     Element
    0.08
     Keep
    0.08
     Galaxy
    0.08
    -ko
    0.07
     Lif
    0.07
     Synchron
    0.07
     Stopwatch
    0.07
    иров
    0.07
    0.07
     Buck
    0.07
    Activations Density 0.001%

    No Known Activations