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. 42497
    Prev
    Next
    INDEX
    Explanations

    code

    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
    bruch
    -0.09
    łącz
    -0.08
    �
    -0.08
     infatti
    -0.08
    (ir
    -0.08
     officiellement
    -0.08
     رسمی
    -0.08
     //(
    -0.07
    -fat
    -0.07
     tablo
    -0.07
    POSITIVE LOGITS
    oor
    0.08
     sufr
    0.08
    角
    0.07
     fie
    0.07
    ani
    0.07
    123
    0.07
    .S
    0.07
    қы
    0.07
     array
    0.07
    event
    0.07
    Activations Density 0.029%

    No Known Activations