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. 76514
    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
    eno
    -0.08
     conç
    -0.08
    虹
    -0.07
    _Str
    -0.07
    Subsystem
    -0.07
     instincts
    -0.07
    ütter
    -0.07
    EXIT
    -0.07
    luetooth
    -0.07
     thoughtfully
    -0.07
    POSITIVE LOGITS
    .folder
    0.08
    .li
    0.08
     
    0.07
     liy
    0.07
    ,index
    0.07
     зан
    0.07
    .Company
    0.07
     համ
    0.07
     Folder
    0.07
     priv
    0.07
    Activations Density 0.001%

    No Known Activations