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. 113883
    Prev
    Next
    INDEX
    Explanations

    Counting characters

    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
    その
    -0.08
    .DOWN
    -0.08
     lois
    -0.08
    不是
    -0.07
    ద్�
    -0.07
    ö
    -0.07
     och
    -0.07
    OTES
    -0.07
     Crawford
    -0.06
     legis
    -0.06
    POSITIVE LOGITS
     Mediterr
    0.10
     многое
    0.10
    something
    0.09
    heres
    0.08
     türk
    0.08
    Something
    0.08
     parsley
    0.08
    however
    0.08
     অথবা
    0.08
     Something
    0.08
    Activations Density 0.019%

    No Known Activations