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. 53580
    Prev
    Next
    INDEX
    Explanations

    can

    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
     slogan
    -0.09
    倡
    -0.09
     MOQ
    -0.08
     Sell
    -0.08
     technologically
    -0.08
     강조
    -0.08
     фун
    -0.07
    ੰਡ
    -0.07
    宣
    -0.07
     blouse
    -0.07
    POSITIVE LOGITS
     browsing
    0.09
    <|message|>
    0.08
     GPT
    0.08
     myself
    0.08
     Zugriff
    0.08
     recall
    0.08
     recalling
    0.08
     brute
    0.07
     offline
    0.07
     beina
    0.07
    Activations Density 0.024%

    No Known Activations