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. 52868
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     //$
    -0.09
    様
    -0.08
    zać
    -0.08
    去了
    -0.08
    Configs
    -0.08
     herein
    -0.08
    harib
    -0.08
    anku
    -0.08
    //$
    -0.08
    ilities
    -0.08
    POSITIVE LOGITS
     использованием
    0.08
     Explicit
    0.08
     simpler
    0.08
     langsung
    0.08
     воспользоваться
    0.08
     ifad
    0.08
     diretamente
    0.08
     explicit
    0.07
    の場合
    0.07
    .listen
    0.07
    Activations Density 0.051%

    No Known Activations