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. 77861
    Prev
    Next
    INDEX
    Explanations

    print

    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
     theme
    -0.08
     Lange
    -0.08
     atrás
    -0.08
     Character
    -0.08
     हिंदी
    -0.08
     लाग
    -0.08
     Intel
    -0.08
    琳
    -0.07
     Caracter
    -0.07
     Sentence
    -0.07
    POSITIVE LOGITS
    opio
    0.08
    Prem
    0.08
     organism
    0.08
     commodo
    0.08
    (){
    ↵
    0.08
     såsom
    0.08
    prem
    0.08
    jit
    0.08
     AGR
    0.08
    live
    0.08
    Activations Density 0.001%

    No Known Activations