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. 103407
    Prev
    Next
    INDEX
    Explanations

    Technical and multilingual texts

    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
     thrill
    -0.09
     拼
    -0.08
     thrilled
    -0.08
    nz
    -0.08
    -pound
    -0.08
     noun
    -0.07
     pound
    -0.07
     fret
    -0.07
     papier
    -0.07
     delin
    -0.07
    POSITIVE LOGITS
     soothing
    0.16
     calming
    0.14
     soothe
    0.13
     শান্ত
    0.13
     concili
    0.12
     शांत
    0.11
     peaceful
    0.11
     tranquility
    0.11
     beruh
    0.11
     amel
    0.10
    Activations Density 0.009%

    No Known Activations