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. 90280
    Prev
    Next
    INDEX
    Explanations

    delimiters/separators

    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
    _kel
    -0.09
    ."_
    -0.08
     bekom
    -0.08
     zweiten
    -0.08
    aylor
    -0.08
     merk
    -0.08
     "_
    -0.08
    ക്കുന്ന
    -0.08
     drast
    -0.08
     থাকা
    -0.07
    POSITIVE LOGITS
     importantly
    0.09
    0.08
     기타
    0.08
     stated
    0.07
    uls
    0.07
     mostr
    0.07
     mostly
    0.07
     delivers
    0.07
    unted
    0.07
     largely
    0.07
    Activations Density 0.071%

    No Known Activations