© 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. 31273
    Prev
    Next
    INDEX
    Explanations

    slipping or rolling

    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
    가입
    -0.08
     copyright
    -0.08
     incentives
    -0.08
    067
    -0.08
     franchise
    -0.08
    책
    -0.07
    평
    -0.07
    069
    -0.07
    Howdy
    -0.07
     zoo
    -0.07
    POSITIVE LOGITS
    涙
    0.13
     lágrimas
    0.12
    滴
    0.11
     lágr
    0.10
     น้ำ
    0.10
    液
    0.10
     gesammelt
    0.10
    汗
    0.09
    �
    0.09
     pudd
    0.09
    Activations Density 0.017%

    No Known Activations