© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2791
    Prev
    Next
    INDEX
    Explanations

    steganography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pose
    -0.08
    _pose
    -0.08
     posing
    -0.08
     soreness
    -0.08
     traction
    -0.08
     vitre
    -0.08
     virtuelle
    -0.07
     poses
    -0.07
     Fuel
    -0.07
     overzicht
    -0.07
    POSITIVE LOGITS
    .encode
    0.09
     encoded
    0.09
     packets
    0.09
     transmitted
    0.09
    Bits
    0.08
     bits
    0.08
    Packed
    0.08
     áo
    0.08
     Bits
    0.08
     ಮಾ�
    0.08
    Activations Density 0.024%

    No Known Activations