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. 88135
    Prev
    Next
    INDEX
    Explanations

    audio production

    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
     기자
    -0.08
    寓
    -0.08
    Charm
    -0.08
    aptor
    -0.08
    MLE
    -0.08
     cubierta
    -0.08
     alin
    -0.08
    涵
    -0.08
    નિક
    -0.08
    िक्त
    -0.08
    POSITIVE LOGITS
     louder
    0.12
     amplitude
    0.11
     loud
    0.11
     clipping
    0.10
     vocals
    0.09
     amplit
    0.09
     audio
    0.09
     audible
    0.09
    .audio
    0.09
     attenuation
    0.09
    Activations Density 0.007%

    No Known Activations