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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97676
    Prev
    Next
    INDEX
    Explanations

    K

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.09
    going
    -0.08
    ��
    -0.07
    まあ
    -0.07
    됨
    -0.07
     cuerpo
    -0.07
    겨
    -0.07
     �
    -0.07
     iterations
    -0.07
    niers
    -0.07
    POSITIVE LOGITS
    hatik
    0.16
    hand
    0.15
    ృష్ణ
    0.14
    ൃഷ്ണ
    0.14
    hañ
    0.13
    umar
    0.13
    handa
    0.13
    ukkut
    0.13
    shit
    0.12
    aly
    0.12
    Activations Density 0.010%

    No Known Activations