Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 29920
    Prev
    Next
    INDEX
    Explanations

    Japanese language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ાઓ
    -0.09
    Bart
    -0.09
     Bart
    -0.08
    ाएं
    -0.08
    ाओं
    -0.08
    дық
    -0.07
    Playback
    -0.07
    .exercise
    -0.07
    ారణ
    -0.07
     pall
    -0.07
    POSITIVE LOGITS
    キ
    0.09
    セ
    0.09
    ド
    0.09
    ク
    0.09
    メリ
    0.08
    ンサ
    0.08
    ヒ
    0.08
    ーマ
    0.08
    マ
    0.08
    ケ
    0.08
    Activations Density 0.015%

    No Known Activations