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. 112251
    Prev
    Next
    INDEX
    Explanations

    >

    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
     inaccurate
    -0.08
     لع
    -0.08
    chec
    -0.08
     accurate
    -0.07
    /ip
    -0.07
    own
    -0.07
    Archives
    -0.07
     luminous
    -0.07
     greenhouse
    -0.07
     intr
    -0.07
    POSITIVE LOGITS
    .With
    0.09
     wiederum
    0.08
     Stärke
    0.07
    eri
    0.07
    enzie
    0.07
    анал
    0.07
    .bulk
    0.07
    ️
    0.07
     borne
    0.07
     rassemble
    0.07
    Activations Density 0.010%

    No Known Activations