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. 101580
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities

    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
    ENT
    -0.08
     CIR
    -0.08
     Everton
    -0.07
    هِ
    -0.07
    �
    -0.07
     Hodg
    -0.07
    balls
    -0.07
    coins
    -0.07
    Defs
    -0.07
     Rates
    -0.07
    POSITIVE LOGITS
     தன
    0.09
     மருத்துவ
    0.08
    оприят
    0.08
     неп
    0.08
     לנ
    0.08
    .Non
    0.08
     ஒரு
    0.08
     அல
    0.08
    대로
    0.08
     ал
    0.08
    Activations Density 0.008%

    No Known Activations