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. 98623
    Prev
    Next
    INDEX
    Explanations

    Mot

    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
     medicamentos
    -0.08
    тые
    -0.08
    ativo
    -0.08
    Auth
    -0.08
    hm
    -0.08
    aturas
    -0.08
     lendo
    -0.08
    ated
    -0.07
    alen
    -0.07
    Read
    -0.07
    POSITIVE LOGITS
     importantly
    0.08
    -cultural
    0.08
     있게
    0.08
     seven
    0.08
    իվ
    0.08
     motives
    0.08
     zeven
    0.08
    изацию
    0.07
    -Code
    0.07
     subclass
    0.07
    Activations Density 0.002%

    No Known Activations