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. 54046
    Prev
    Next
    INDEX
    Explanations

    an

    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
     Lopes
    -0.09
    汽
    -0.08
     softened
    -0.08
    నే
    -0.07
     ped
    -0.07
     संभ
    -0.07
     grav
    -0.07
     duk
    -0.07
     necesit
    -0.07
    汇
    -0.07
    POSITIVE LOGITS
    cline
    0.08
     strand
    0.07
    gebnisse
    0.07
     junk
    0.07
    iot
    0.07
     definitions
    0.07
     Dry
    0.07
     bent
    0.07
     Clos
    0.07
    Clos
    0.07
    Activations Density 0.184%

    No Known Activations