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. 112845
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    mainwindow
    -0.09
    utar
    -0.09
     capacitación
    -0.08
     quaternion
    -0.08
    Radius
    -0.08
    _RADIUS
    -0.08
    für
    -0.08
    før
    -0.08
    ubuntu
    -0.08
    wet
    -0.08
    POSITIVE LOGITS
     Unique
    0.11
    Unique
    0.11
     уник
    0.10
    <Guid
    0.09
     idx
    0.09
     indeks
    0.09
    _unique
    0.08
    索
    0.08
    /id
    0.08
    .id
    0.08
    Activations Density 0.002%

    No Known Activations