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. 102668
    Prev
    Next
    INDEX
    Explanations

    Code/Kernel Functions

    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
     HR
    -0.09
    _avatar
    -0.08
     мах
    -0.08
    钢
    -0.07
     cro
    -0.07
     stup
    -0.07
    -0.07
     zar
    -0.07
     incontournable
    -0.07
    :The
    -0.07
    POSITIVE LOGITS
    ১৪
    0.08
    ��
    0.08
    oseconds
    0.08
    illiseconds
    0.08
    ĩ
    0.08
     formulier
    0.08
    kl
    0.08
    asking
    0.08
    uose
    0.08
    ეს
    0.08
    Activations Density 0.001%

    No Known Activations