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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68943
    Prev
    Next
    INDEX
    Explanations

    reasons, motivations

    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
    (f
    -0.08
    :f
    -0.08
     �
    -0.08
    ��
    -0.08
    Qed
    -0.07
    (axis
    -0.07
    (strict
    -0.07
    onn
    -0.07
    [f
    -0.07
    иваются
    -0.07
    POSITIVE LOGITS
     ताकि
    0.14
    为了
    0.14
    เพื่อ
    0.14
     כדי
    0.13
     بهدف
    0.13
     azért
    0.12
     تاکہ
    0.12
     alasan
    0.12
     nhằm
    0.12
    旨
    0.11
    Activations Density 0.203%

    No Known Activations