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. 98164
    Prev
    Next
    INDEX
    Explanations

    slightly

    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
     huge
    -0.10
     énorm
    -0.10
     Huge
    -0.10
     enormous
    -0.10
    _ALWAYS
    -0.10
     барлық
    -0.10
     ALWAYS
    -0.10
     énorme
    -0.09
     반드시
    -0.09
    Huge
    -0.09
    POSITIVE LOGITS
     slight
    0.45
     थोड़ा
    0.43
     slightly
    0.43
     слегка
    0.42
     légèrement
    0.42
     થોડ
    0.41
     ligeramente
    0.41
     немного
    0.40
     थो
    0.40
     sedikit
    0.40
    Activations Density 0.987%

    No Known Activations