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. 55107
    Prev
    Next
    INDEX
    Explanations

    information

    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
     tjen
    -0.08
    登陆
    -0.08
     <<↵
    -0.08
     servizi
    -0.08
     routine
    -0.08
     पर
    -0.07
    routine
    -0.07
    _SERV
    -0.07
    ober
    -0.07
    及
    -0.07
    POSITIVE LOGITS
     conveyed
    0.11
    information
    0.11
     информации
    0.10
     glean
    0.09
    .Information
    0.09
     information
    0.09
    -bearing
    0.09
     inherent
    0.09
    vollen
    0.09
    .intent
    0.09
    Activations Density 0.018%

    No Known Activations