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. 97115
    Prev
    Next
    INDEX
    Explanations

    Positive sentiment in Russian

    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
    -thread
    -0.10
     Anteil
    -0.09
     பகுதியில்
    -0.09
    వారం
    -0.09
     ماده
    -0.09
     σειρά
    -0.09
     dimensión
    -0.08
    දේශ
    -0.08
    -日本
    -0.08
    ಭ
    -0.08
    POSITIVE LOGITS
     голос
    0.11
     настрой
    0.09
    ими
    0.09
     рассказ
    0.09
     hlas
    0.09
    ун
    0.08
     народ
    0.08
    াকে
    0.08
     город
    0.08
    sey
    0.08
    Activations Density 0.011%

    No Known Activations