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. 11-RESID-POST-AA
    6. 75913
    Prev
    Next
    INDEX
    Explanations

    �

    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
     doğ
    -0.08
     luar
    -0.08
     Formación
    -0.08
    按照
    -0.07
     Enkel
    -0.07
     Poss
    -0.07
    akespeare
    -0.07
     reden
    -0.07
     GOOD
    -0.07
    绕
    -0.07
    POSITIVE LOGITS
    ────────────────
    0.09
    ────────
    0.08
    192
    0.08
    Safety
    0.08
    (C
    0.08
    adv
    0.08
    Extend
    0.08
    axi
    0.08
     accommodating
    0.07
     tee
    0.07
    Activations Density 0.001%

    No Known Activations