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. 12224
    Prev
    Next
    INDEX
    Explanations

    hearing

    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
     நடந்த
    -0.08
    ೊಬ್ಬ
    -0.08
     glycol
    -0.08
     Ferm
    -0.07
     вокруг
    -0.07
     teria
    -0.07
    ાર
    -0.07
     Gly
    -0.07
     જીત
    -0.07
     Garg
    -0.07
    POSITIVE LOGITS
     impairment
    0.09
     impair
    0.09
    觉
    0.09
     auditory
    0.09
     শুন
    0.08
     നഷ്ട
    0.08
     নিউ
    0.08
     আক্রান্ত
    0.08
    াইট
    0.08
    -vit
    0.08
    Activations Density 0.005%

    No Known Activations