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. 43619
    Prev
    Next
    INDEX
    Explanations

    .

    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
     بی
    -0.08
     투
    -0.08
     Satell
    -0.08
     stones
    -0.08
     satellites
    -0.08
     plaques
    -0.07
    Lab
    -0.07
     قانون
    -0.07
     evac
    -0.07
     بالا
    -0.07
    POSITIVE LOGITS
     confirmó
    0.09
    ;.
    0.09
    िता
    0.08
    итися
    0.08
    icherheit
    0.08
    орно
    0.08
    。(
    0.07
    。(
    0.07
    raphics
    0.07
    (serv
    0.07
    Activations Density 0.714%

    No Known Activations