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. 111628
    Prev
    Next
    INDEX
    Explanations

    Midjourney prompt generation

    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
     Calif
    -0.08
    attan
    -0.08
    ланған
    -0.08
     التن
    -0.08
     railing
    -0.07
    angi
    -0.07
    anjang
    -0.07
     unat
    -0.07
     establece
    -0.07
    æn
    -0.07
    POSITIVE LOGITS
    .exe
    0.08
    .com
    0.08
    ®
    0.07
     OBS
    0.07
     számára
    0.07
     olm
    0.07
     newer
    0.07
     Prospect
    0.07
    救世
    0.07
     NB
    0.07
    Activations Density 0.007%

    No Known Activations