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. 631
    Prev
    Next
    INDEX
    Explanations

    prompt

    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
    dots
    -0.08
     red
    -0.07
     Pap
    -0.07
     MOS
    -0.07
    red
    -0.07
    红
    -0.07
     blues
    -0.07
     fault
    -0.07
     semic
    -0.07
     Require
    -0.07
    POSITIVE LOGITS
     nuance
    0.09
     experimented
    0.09
     Stevie
    0.09
     Potter
    0.08
    技巧
    0.08
     Tricks
    0.08
    텔
    0.08
     �
    0.08
    Puedes
    0.08
     ventured
    0.08
    Activations Density 0.003%

    No Known Activations