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. 98251
    Prev
    Next
    INDEX
    Explanations

    est

    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
    ávamos
    -0.08
    พร
    -0.08
    essian
    -0.08
     تای
    -0.08
     객체
    -0.08
    łości
    -0.07
    arel
    -0.07
     bewust
    -0.07
    ablishment
    -0.07
    회사
    -0.07
    POSITIVE LOGITS
    erase
    0.11
    atus
    0.10
    andar
    0.09
    ifstream
    0.08
    atico
    0.08
    erna
    0.08
    andard
    0.08
    atic
    0.07
    icator
    0.07
    óf
    0.07
    Activations Density 0.001%

    No Known Activations