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. 12498
    Prev
    Next
    INDEX
    Explanations

    d

    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
     jis
    -0.08
     дав
    -0.08
     साल
    -0.07
    Sect
    -0.07
     چی
    -0.07
    ope
    -0.07
    /star
    -0.07
     chiffre
    -0.07
     normalmente
    -0.07
     bref
    -0.07
    POSITIVE LOGITS
    尼
    0.08
     Hol
    0.08
     неё
    0.07
     tej
    0.07
     Sole
    0.07
     Rac
    0.07
    ൻ
    0.07
     ANT
    0.07
    -sac
    0.07
     Watt
    0.07
    Activations Density 0.001%

    No Known Activations