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. 98035
    Prev
    Next
    INDEX
    Explanations

    Св

    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
    ATORY
    -0.09
    šanas
    -0.08
    igens
    -0.08
    ASURE
    -0.08
     knie
    -0.07
    šnj
    -0.07
    viz
    -0.07
     steep
    -0.07
    gings
    -0.07
     stro
    -0.07
    POSITIVE LOGITS
    обод
    0.18
    язан
    0.16
    яз
    0.15
    яж
    0.13
    орач
    0.12
    यं
    0.12
    еж
    0.11
    я
    0.11
    ास्थ्य
    0.11
    ой
    0.11
    Activations Density 0.001%

    No Known Activations