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. 58338
    Prev
    Next
    INDEX
    Explanations

    Arabic and Chinese languages

    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
    _ELEMENT
    -0.09
     insects
    -0.08
    _IN
    -0.08
     insect
    -0.08
    _in
    -0.08
    (.)
    -0.08
    .count
    -0.07
     gigant
    -0.07
    �
    -0.07
    👉
    -0.07
    POSITIVE LOGITS
    urt
    0.08
     Meh
    0.07
    irió
    0.07
    hb
    0.07
     fun
    0.07
    uclear
    0.07
     hö
    0.07
     permita
    0.07
    alt
    0.07
    рана
    0.07
    Activations Density 0.011%

    No Known Activations