© 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. 11-RESID-POST-AA
    11. 78500
    Prev
    Next
    INDEX
    Explanations

    parity of flips

    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
     vendas
    -0.08
     sales
    -0.08
     �
    -0.07
     Schon
    -0.07
     Maori
    -0.07
     Sales
    -0.07
     Lawson
    -0.07
     vender
    -0.07
     vend
    -0.07
    销售
    -0.07
    POSITIVE LOGITS
     rotations
    0.11
     clockwise
    0.10
     воздействия
    0.09
     toggle
    0.09
    .rotate
    0.09
     togg
    0.09
     rotates
    0.09
     rotate
    0.08
    _rot
    0.08
    風吹
    0.08
    Activations Density 0.007%

    No Known Activations