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. 58296
    Prev
    Next
    INDEX
    Explanations

    goes wrong

    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
     생성
    -0.08
    ismod
    -0.07
    quantity
    -0.07
    Fake
    -0.07
     detectable
    -0.07
    AVE
    -0.07
    if
    -0.07
    instit
    -0.07
    iele
    -0.07
     oluştur
    -0.07
    POSITIVE LOGITS
    失败
    0.14
     실패
    0.12
     unforeseen
    0.11
     failures
    0.11
     disastr
    0.11
     malfunction
    0.11
     mish
    0.11
     FAIL
    0.11
    	perror
    0.11
     disastrous
    0.10
    Activations Density 0.066%

    No Known Activations