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. 65709
    Prev
    Next
    INDEX
    Explanations

    nid

    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
    posts
    -0.08
    -post
    -0.07
    topics
    -0.07
    olders
    -0.07
    tags
    -0.07
    做
    -0.07
    PAD
    -0.07
    assets
    -0.07
     rejection
    -0.07
    CK
    -0.07
    POSITIVE LOGITS
     kopi
    0.08
     Spazier
    0.08
     dizem
    0.08
    ,请
    0.07
    “If
    0.07
     Bever
    0.07
     dx
    0.07
    “There
    0.07
    ujú
    0.07
    イ
    0.07
    Activations Density 0.000%

    No Known Activations