© 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. 129443
    Prev
    Next
    INDEX
    Explanations

    Jewelry descriptions

    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
     entraîne
    -0.08
    Facility
    -0.07
     vastly
    -0.07
     درس
    -0.07
    خة
    -0.07
    Orm
    -0.07
    variables
    -0.07
    ੂ
    -0.07
    -rom
    -0.07
    -на
    -0.07
    POSITIVE LOGITS
    尺寸
    0.10
     sleeve
    0.08
     protr
    0.08
     convertible
    0.08
     kement
    0.08
     watercolor
    0.08
     tiny
    0.07
     Ltd
    0.07
     �
    0.07
    /icons
    0.07
    Activations Density 0.030%

    No Known Activations