Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11895
    Prev
    Next
    INDEX
    Explanations

    option

    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
    부터
    -0.08
    Cro
    -0.08
    _OV
    -0.08
     continual
    -0.08
    _OP
    -0.08
     aru
    -0.08
    GAIN
    -0.07
     들
    -0.07
     Kuwait
    -0.07
     ble
    -0.07
    POSITIVE LOGITS
     Shadow
    0.08
    Shadow
    0.08
     ਜਿਸ
    0.08
    _shadow
    0.08
    shadow
    0.07
    handlung
    0.07
    fav
    0.07
     sombras
    0.07
     рассмотр
    0.07
    -shadow
    0.07
    Activations Density 0.016%

    No Known Activations