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. 90138
    Prev
    Next
    INDEX
    Explanations

    Defining sequences

    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
    kter
    -0.09
    .Window
    -0.09
    Window
    -0.08
     tact
    -0.08
    Analy
    -0.08
    ేక
    -0.08
    -window
    -0.08
     assessing
    -0.08
     assessments
    -0.08
    _window
    -0.08
    POSITIVE LOGITS
     diber
    0.09
     정의
    0.08
     тав
    0.08
     вроде
    0.08
     repeatedly
    0.08
     правила
    0.08
     Initialise
    0.08
     규
    0.08
     б
    0.08
     induct
    0.08
    Activations Density 0.032%

    No Known Activations