© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44870
    Prev
    Next
    INDEX
    Explanations

    code

    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
     infiltr
    -0.09
    �
    -0.08
     الع
    -0.08
    सं
    -0.08
     eingestellt
    -0.08
    态
    -0.08
    朝
    -0.08
     온
    -0.08
    érature
    -0.08
    �
    -0.08
    POSITIVE LOGITS
    ow
    0.09
    duplicates
    0.08
    gre
    0.08
    -c
    0.07
    lowest
    0.07
    patch
    0.07
    trs
    0.07
     CSI
    0.07
    elin
    0.07
    vision
    0.07
    Activations Density 0.029%

    No Known Activations