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. 111788
    Prev
    Next
    INDEX
    Explanations

    =>

    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
     frag
    -0.08
    にも
    -0.08
     precautions
    -0.08
     Amp
    -0.07
     Frag
    -0.07
     intrins
    -0.07
    增
    -0.07
    122
    -0.07
     vantage
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     FH
    0.08
     schn
    0.08
     financier
    0.08
     GHz
    0.07
     MAG
    0.07
     Herstell
    0.07
     nation's
    0.07
     Taylor
    0.07
     bilateral
    0.07
    คุณ
    0.07
    Activations Density 0.005%

    No Known Activations