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. 49390
    Prev
    Next
    INDEX
    Explanations

    row

    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
    -0.08
    _enqueue
    -0.08
     notch
    -0.07
     abandon
    -0.07
     dispositions
    -0.07
     sq
    -0.07
     matang
    -0.07
     rad
    -0.07
    _probe
    -0.07
    -0.07
    POSITIVE LOGITS
     correspondant
    0.10
    代表
    0.09
    ,每
    0.09
     Correspond
    0.08
     referente
    0.08
     correspondente
    0.08
    对应
    0.08
    子
    0.08
    ાંત
    0.08
    enga
    0.08
    Activations Density 0.024%

    No Known Activations