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. 130802
    Prev
    Next
    INDEX
    Explanations

    ar

    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
     qu
    -0.08
    (dict
    -0.08
     genn
    -0.08
     quedaron
    -0.07
     سنڌ
    -0.07
     homelessness
    -0.07
     proph
    -0.07
    決
    -0.07
     जीत
    -0.07
     уровне
    -0.07
    POSITIVE LOGITS
     anxious
    0.08
     vigilant
    0.08
    utte
    0.07
    υ
    0.07
    باح
    0.07
     rett
    0.07
     worried
    0.07
    nými
    0.07
    aud
    0.07
     вним
    0.07
    Activations Density 0.000%

    No Known Activations