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. 15-RESID-POST-AA
    6. 18992
    Prev
    Next
    INDEX
    Explanations

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .ver
    -0.08
    parate
    -0.08
     evidenced
    -0.08
     the
    -0.08
    future
    -0.07
    -aga
    -0.07
     fate
    -0.07
    -Ver
    -0.07
    stechn
    -0.07
    sha
    -0.07
    POSITIVE LOGITS
     proposés
    0.10
     ellers
    0.09
     ofrec
    0.09
     OTHERWISE
    0.09
     proposées
    0.08
    átiles
    0.08
    请选择
    0.08
     밖
    0.08
    任选
    0.08
     ansonsten
    0.07
    Activations Density 0.024%

    No Known Activations