© 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. 78092
    Prev
    Next
    INDEX
    Explanations

    geometric orientation

    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
    یه
    -0.08
     lifes
    -0.08
     meteor
    -0.07
    netje
    -0.07
     uh
    -0.07
     Trick
    -0.07
     конди
    -0.07
     מוס
    -0.07
    atted
    -0.07
     belg
    -0.07
    POSITIVE LOGITS
    _THAN
    0.10
    _than
    0.09
     чем
    0.08
     than
    0.08
     entregar
    0.08
     чым
    0.08
     priori
    0.08
    Locked
    0.08
     যেতে
    0.08
    wards
    0.08
    Activations Density 0.015%

    No Known Activations