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. 3-RESID-POST-AA
    6. 2336
    Prev
    Next
    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Needle
    -0.09
     Klein
    -0.08
     needle
    -0.08
     Pań
    -0.08
     Nixon
    -0.07
    ZS
    -0.07
     Hul
    -0.07
    ?!
    -0.07
     поставить
    -0.07
     fim
    -0.07
    POSITIVE LOGITS
    бы
    0.08
     callable
    0.08
     upbringing
    0.08
     аны
    0.08
    ાળ
    0.07
     �
    0.07
     certain
    0.07
    isang
    0.07
    逐
    0.07
     royalty
    0.07
    Activations Density 0.000%

    No Known Activations