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. 90201
    Prev
    Next
    INDEX
    Explanations

    melt

    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
    备
    -0.08
    ład
    -0.08
     deliver
    -0.07
    ائي
    -0.07
    {}{
    -0.07
    #"
    -0.07
    czę
    -0.07
    章
    -0.07
     seismic
    -0.07
     intercept
    -0.07
    POSITIVE LOGITS
    掉
    0.11
     lentamente
    0.11
     langsam
    0.10
     slowly
    0.10
     Slowly
    0.09
     doucement
    0.09
    Tutorial
    0.09
     soot
    0.09
    徐
    0.09
     �
    0.09
    Activations Density 0.009%

    No Known Activations