Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98080
    Prev
    Next
    INDEX
    Explanations

    ин

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    로운
    -0.09
    ехнолог
    -0.09
    otechnology
    -0.08
     профес
    -0.08
     profesion
    -0.08
     Cobra
    -0.08
     teknoloj
    -0.08
    ្មី
    -0.08
     pug
    -0.08
    рофессион
    -0.08
    POSITIVE LOGITS
    大陆
    0.14
     continental
    0.14
     continents
    0.13
     continent
    0.13
     continente
    0.12
    continental
    0.12
     Continental
    0.12
     Europe
    0.12
    continent
    0.12
    frica
    0.11
    Activations Density 0.005%

    No Known Activations