© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1054
    Prev
    Next
    INDEX
    Explanations

    cess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raid
    -0.08
    eliers
    -0.08
     obra
    -0.08
     staircase
    -0.08
     idir
    -0.08
     օդ
    -0.08
     SIP
    -0.07
     Herzog
    -0.07
     स्थाप
    -0.07
    动车
    -0.07
    POSITIVE LOGITS
     Gez
    0.08
    NBT
    0.07
    NA
    0.07
    NP
    0.07
     People
    0.07
    Kinder
    0.07
     život
    0.07
     glän
    0.07
     glim
    0.07
     judging
    0.07
    Activations Density 0.000%

    No Known Activations