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. 112250
    Prev
    Next
    INDEX
    Explanations

    bitwise rotation, programming

    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
    avenir
    -0.09
    visitor
    -0.08
     મુલાકાત
    -0.08
    导师
    -0.08
     inspectors
    -0.08
    piece
    -0.08
    ک
    -0.08
    aviors
    -0.08
    骗子
    -0.08
     bezocht
    -0.08
    POSITIVE LOGITS
     rotation
    0.11
    .rotate
    0.11
     rotate
    0.11
     shift
    0.10
    rotate
    0.10
     Rotate
    0.10
     skb
    0.10
     clockwise
    0.09
     rotations
    0.09
     rotates
    0.09
    Activations Density 0.004%

    No Known Activations