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. 102970
    Prev
    Next
    INDEX
    Explanations

    value

    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
     freie
    -0.08
    @yahoo
    -0.07
     enumer
    -0.07
     ಮೊ
    -0.07
    雀
    -0.07
     homogeneous
    -0.07
     radiation
    -0.07
    ........................
    -0.07
    roid
    -0.07
     nationality
    -0.07
    POSITIVE LOGITS
    uestran
    0.08
    μένου
    0.07
     liens
    0.07
    링
    0.07
    ящего
    0.07
    链
    0.07
    μμ
    0.07
     NU
    0.07
    옵
    0.07
    인은
    0.07
    Activations Density 0.001%

    No Known Activations