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. 119247
    Prev
    Next
    INDEX
    Explanations

    Formatting symbols

    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
     Подробнее
    -0.08
     বেশি
    -0.08
     ix
    -0.08
    förder
    -0.07
     ఎక్కువ
    -0.07
    _self
    -0.07
     איש
    -0.07
     german
    -0.07
     appropr
    -0.07
     принцип
    -0.07
    POSITIVE LOGITS
    sip
    0.08
     schließlich
    0.08
    ').
    0.08
     ema
    0.08
     finalize
    0.08
    Finally
    0.08
     speeches
    0.08
     Natalie
    0.08
     interação
    0.07
     spindle
    0.07
    Activations Density 0.036%

    No Known Activations