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. 103028
    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
     spontaneously
    -0.09
    -0.07
     Dad
    -0.07
     tek
    -0.07
     Apartments
    -0.07
     spouse
    -0.07
    抵
    -0.07
    alig
    -0.07
    /be
    -0.07
     amplifier
    -0.07
    POSITIVE LOGITS
    ένα
    0.08
    864
    0.08
    Qué
    0.08
    405
    0.08
    130
    0.07
    465
    0.07
    857
    0.07
     él
    0.07
    330
    0.07
    310
    0.07
    Activations Density 0.015%

    No Known Activations