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. 59950
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
    ريان
    -0.08
     EK
    -0.08
    CCD
    -0.08
    RF
    -0.07
    .Butter
    -0.07
    ាតិ
    -0.07
    .Em
    -0.07
    -art
    -0.07
     Art
    -0.07
     UE
    -0.07
    POSITIVE LOGITS
     במקרה
    0.09
     […
    0.09
    whatever
    0.08
    なん
    0.08
    ommer
    0.08
     gaming
    0.08
     whatever
    0.07
    etc
    0.07
    /operators
    0.07
    “…
    0.07
    Activations Density 0.341%

    No Known Activations