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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1087
    Prev
    Next
    INDEX
    Explanations

    image coordinates

    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
     carr
    -0.08
    ッ
    -0.07
    orrection
    -0.07
    re
    -0.07
    dus
    -0.07
     probation
    -0.07
     sommes
    -0.07
    iness
    -0.07
    Mind
    -0.07
    :
    -0.07
    POSITIVE LOGITS
     climatique
    0.08
     Gl
    0.08
     WHEN
    0.08
     Coorden
    0.08
     glut
    0.08
     Durch
    0.08
     urrainn
    0.08
     координ
    0.08
     climático
    0.08
     coorden
    0.07
    Activations Density 0.002%

    No Known Activations