© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51348
    Prev
    Next
    INDEX
    Explanations

    say "生 character"

    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
     iespēj
    -0.08
     sellele
    -0.08
     검
    -0.08
     Kü
    -0.08
    orero
    -0.07
    undu
    -0.07
     zdaj
    -0.07
    ueuse
    -0.07
    abilis
    -0.07
    oucou
    -0.07
    POSITIVE LOGITS
    生
    0.19
     生
    0.16
    생
    0.13
    伸
    0.11
    生产
    0.11
     생
    0.10
    、生
    0.10
    生活
    0.10
     sinh
    0.10
     biotechnology
    0.09
    Activations Density 0.000%

    No Known Activations