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. 130290
    Prev
    Next
    INDEX
    Explanations

    less

    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
     cakes
    -0.08
     brownies
    -0.08
    cookies
    -0.08
    _cookie
    -0.08
     wrath
    -0.07
     youtube
    -0.07
     День
    -0.07
     Blizzard
    -0.07
    คิด
    -0.07
     parametr
    -0.07
    POSITIVE LOGITS
    Hin
    0.08
     Lightweight
    0.08
     overeen
    0.08
     forbind
    0.08
     recién
    0.08
    .Ribbon
    0.08
     petite
    0.08
     lightweight
    0.07
     sampled
    0.07
     retract
    0.07
    Activations Density 0.001%

    No Known Activations