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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 26782
    Prev
    Next
    INDEX
    Explanations

    audio/video transcription

    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
    -tier
    -0.09
     conduit
    -0.08
    مط
    -0.08
     блюда
    -0.08
     undertaken
    -0.08
     کیے
    -0.08
     ciudadanos
    -0.07
     जय
    -0.07
     מסוג
    -0.07
     алған
    -0.07
    POSITIVE LOGITS
     rewind
    0.09
     playback
    0.09
     просмотра
    0.09
    查看
    0.08
    Playback
    0.08
     Playback
    0.08
    播放
    0.08
     zoom
    0.08
     查看
    0.08
     speed
    0.08
    Activations Density 0.010%

    No Known Activations