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. 102979
    Prev
    Next
    INDEX
    Explanations

    .append

    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
    情况下
    -0.08
    lad
    -0.08
     언
    -0.07
     ocean
    -0.07
    igende
    -0.07
    o
    -0.07
     Ocean
    -0.07
     guarda
    -0.07
     بالنسبة
    -0.07
     abrupt
    -0.07
    POSITIVE LOGITS
    进去
    0.09
     echiche
    0.08
     strom
    0.08
     лож
    0.08
    วด
    0.08
     сюда
    0.08
    tuple
    0.08
    Tuple
    0.08
     tuples
    0.08
     stencil
    0.08
    Activations Density 0.007%

    No Known Activations