© 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. 1112
    Prev
    Next
    INDEX
    Explanations

    payment

    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
    র্শ
    -0.08
     unrestricted
    -0.08
    δό
    -0.07
    654
    -0.07
    -house
    -0.07
     portent
    -0.07
    513
    -0.07
    .semantic
    -0.07
    .vector
    -0.07
    qa
    -0.07
    POSITIVE LOGITS
     pudd
    0.08
    握
    0.08
     décon
    0.08
    jeg
    0.07
    搞
    0.07
    nc
    0.07
     drž
    0.07
     açısından
    0.07
     dž
    0.07
     wedding
    0.07
    Activations Density 0.007%

    No Known Activations