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. 49312
    Prev
    Next
    INDEX
    Explanations

    code/grammar related

    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
     Кавказ
    -0.09
    \Data
    -0.09
     عهد
    -0.08
    igitte
    -0.08
     Oma
    -0.08
     الصحية
    -0.08
     afspraak
    -0.08
     ابو
    -0.08
    anzibar
    -0.08
     Physi
    -0.08
    POSITIVE LOGITS
     समाप्त
    0.10
    終
    0.09
     ముగ
    0.08
     composed
    0.08
    coin
    0.08
    _len
    0.08
     USD
    0.08
     roadmap
    0.07
     fs
    0.07
    .ends
    0.07
    Activations Density 0.003%

    No Known Activations