© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95883
    Prev
    Next
    INDEX
    Explanations

    arms

    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
     pathology
    -0.08
    geräte
    -0.08
     ಕುಮ
    -0.08
     orthodont
    -0.08
     ರ
    -0.08
     höf
    -0.08
    راك
    -0.08
     երկ
    -0.07
    gradable
    -0.07
     enthous
    -0.07
    POSITIVE LOGITS
    LV
    0.08
     Performance
    0.08
     LV
    0.08
    VV
    0.07
     lv
    0.07
     Fully
    0.07
     Valve
    0.07
     HV
    0.07
     Kw
    0.07
     Finest
    0.07
    Activations Density 0.000%

    No Known Activations