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. 44062
    Prev
    Next
    INDEX
    Explanations

    vocal cords

    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
     consequential
    -0.08
    _than
    -0.08
     remit
    -0.08
    .an
    -0.08
    td
    -0.07
    .r
    -0.07
     vấn
    -0.07
    ání
    -0.07
     Spencer
    -0.07
    -volume
    -0.07
    POSITIVE LOGITS
     descanso
    0.07
     Encoding
    0.07
    ɑ
    0.07
    猪
    0.07
    801
    0.07
    berger
    0.07
     Parsing
    0.07
     banging
    0.07
     saus
    0.07
    Paused
    0.07
    Activations Density 0.002%

    No Known Activations