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. 102951
    Prev
    Next
    INDEX
    Explanations

    station

    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
     überall
    -0.09
     Alltag
    -0.09
     ಚ
    -0.08
    -au
    -0.08
     billionaire
    -0.08
    angun
    -0.08
     Audi
    -0.08
     Feng
    -0.07
     Stil
    -0.07
     Omni
    -0.07
    POSITIVE LOGITS
     equipments
    0.08
    iyini
    0.08
    wy
    0.08
     majors
    0.08
     serializers
    0.07
     noget
    0.07
    kes
    0.07
    qe
    0.07
    istics
    0.07
     highways
    0.07
    Activations Density 0.000%

    No Known Activations