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. 130791
    Prev
    Next
    INDEX
    Explanations

    Germany's "Energiewende"

    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
    73
    -0.08
     ს
    -0.08
     Safety
    -0.08
    -hours
    -0.08
    'i
    -0.08
    53
    -0.08
    (zone
    -0.07
     решила
    -0.07
     გამ
    -0.07
    ეს
    -0.07
    POSITIVE LOGITS
    IE
    0.09
    তার
    0.08
    o
    0.08
    vien
    0.08
    fac
    0.08
    CDATA
    0.08
    istischen
    0.08
     quotation
    0.08
     ferme
    0.07
     quote
    0.07
    Activations Density 0.001%

    No Known Activations