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. 102847
    Prev
    Next
    INDEX
    Explanations

    invented

    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
     mule
    -0.08
     loaders
    -0.08
    leyen
    -0.08
     presentations
    -0.08
    นั้น
    -0.08
     carreg
    -0.08
    CX
    -0.07
    .messaging
    -0.07
     rendre
    -0.07
     Mule
    -0.07
    POSITIVE LOGITS
    혼
    0.08
     combinatie
    0.07
     Sena
    0.07
    .utc
    0.07
    unlock
    0.07
     прим
    0.07
    -----↵↵
    0.07
     pattern
    0.07
    _two
    0.07
    pattern
    0.07
    Activations Density 0.000%

    No Known Activations