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. 90058
    Prev
    Next
    INDEX
    Explanations

    with/so

    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
    कि
    -0.08
     relatif
    -0.08
     е
    -0.08
     относительно
    -0.08
    еги
    -0.07
    เรา
    -0.07
     виж
    -0.07
    _el
    -0.07
    _engine
    -0.07
     стру
    -0.07
    POSITIVE LOGITS
     nef
    0.08
    ilish
    0.08
     bunun
    0.08
    nef
    0.08
    색
    0.08
    (metrics
    0.08
    dued
    0.08
     Boulder
    0.07
     NATIONAL
    0.07
    (nd
    0.07
    Activations Density 0.000%

    No Known Activations