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. 111927
    Prev
    Next
    INDEX
    Explanations

    Sleep/naps

    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
     du
    -0.08
     saturation
    -0.08
     dud
    -0.08
     duurzaamheid
    -0.08
     puke
    -0.07
    เรียน
    -0.07
     naps
    -0.07
    regen
    -0.07
     dadas
    -0.07
     loco
    -0.07
    POSITIVE LOGITS
    _initialized
    0.08
    vart
    0.08
    _info
    0.08
    ۆ
    0.08
    @Mapper
    0.08
     lätt
    0.08
    wynt
    0.07
     mapper
    0.07
    ichever
    0.07
    zięki
    0.07
    Activations Density 0.001%

    No Known Activations