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. 53964
    Prev
    Next
    INDEX
    Explanations

    structured comparisons

    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
    遗
    -0.07
     Hé
    -0.07
    ύ
    -0.07
    造
    -0.07
    -0.07
     Teil
    -0.07
    -0.07
     Emanuel
    -0.07
     
    -0.06
     Adjustment
    -0.06
    POSITIVE LOGITS
     hingegen
    0.15
     dagegen
    0.11
     naman
    0.09
    則
    0.09
    ilinx
    0.08
     మాత్రం
    0.08
     crisi
    0.08
    >>)
    0.08
    .shutdown
    0.08
    ,you
    0.08
    Activations Density 0.084%

    No Known Activations