© 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. 3-RESID-POST-AA
    11. 886
    Prev
    Next
    INDEX
    Explanations

    는

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пот
    -0.08
    joint
    -0.08
     drift
    -0.08
     hence
    -0.07
    169
    -0.07
     elections
    -0.07
    tou
    -0.07
    वार
    -0.07
     Albert
    -0.07
    otp
    -0.07
    POSITIVE LOGITS
     LA
    0.09
     용
    0.08
    LA
    0.08
     �
    0.08
     argu
    0.08
     Pegasus
    0.08
     Quarter
    0.08
    데
    0.08
     PAL
    0.08
     Victory
    0.08
    Activations Density 0.002%

    No Known Activations