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. 7-RESID-POST-AA
    6. 131020
    Prev
    Next
    INDEX
    Explanations

    spi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Feder
    -0.08
     гум
    -0.08
     hav
    -0.07
     collectivités
    -0.07
     haven
    -0.07
    heure
    -0.07
     compassion
    -0.07
     hemisphere
    -0.07
    Si
    -0.07
     graz
    -0.07
    POSITIVE LOGITS
     Nossa
    0.08
     besch
    0.08
     molten
    0.07
    zuje
    0.07
    0.07
     informative
    0.07
     nas
    0.07
     poř
    0.07
    itchie
    0.07
    :::
    0.07
    Activations Density 0.001%

    No Known Activations