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. 43095
    Prev
    Next
    INDEX
    Explanations

    .t

    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
     shaw
    -0.08
     verpflichtet
    -0.07
    rook
    -0.07
    ahu
    -0.07
     hoeveel
    -0.07
     صرف
    -0.07
    ório
    -0.07
    rrrr
    -0.07
     aanleiding
    -0.07
    jajo
    -0.07
    POSITIVE LOGITS
    ां
    0.08
    /options
    0.08
     hierboven
    0.08
    上述
    0.08
     ऊपर
    0.08
     выше
    0.08
    /screens
    0.07
    /m
    0.07
    Above
    0.07
    adang
    0.07
    Activations Density 0.067%

    No Known Activations