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. 98293
    Prev
    Next
    INDEX
    Explanations

    representations, character

    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
     ergonom
    -0.08
     Lavender
    -0.08
    ounge
    -0.08
     Montessori
    -0.08
     Pare
    -0.08
     restroom
    -0.08
     brainstorming
    -0.08
     hollow
    -0.08
     vip
    -0.08
     શક્ય
    -0.07
    POSITIVE LOGITS
    orial
    0.08
    ries
    0.08
    Functor
    0.08
    .onreadystatechange
    0.08
     Weil
    0.08
     Alf
    0.07
     funer
    0.07
    谋
    0.07
     Honest
    0.07
    NSURL
    0.07
    Activations Density 0.004%

    No Known Activations