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. 98387
    Prev
    Next
    INDEX
    Explanations

    Launch or release

    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
     oefeningen
    -0.08
     exercises
    -0.08
     ejercicios
    -0.08
     convicted
    -0.08
     Einkommen
    -0.08
    学历
    -0.08
     Gemeinden
    -0.08
     wohnen
    -0.08
     accum
    -0.08
     упражнения
    -0.08
    POSITIVE LOGITS
     출시
    0.47
     lanzamiento
    0.43
     lancement
    0.43
     lançamento
    0.42
     launch
    0.42
     लॉन्च
    0.42
     ಬಿಡುಗಡೆ
    0.41
     ಬಿಡುಗ
    0.40
    推出
    0.39
     release
    0.39
    Activations Density 0.387%

    No Known Activations