© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    mer

    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
    ances
    -0.07
    Cup
    -0.07
    악
    -0.07
    nc
    -0.07
     malignant
    -0.07
     Aberdeen
    -0.07
     abduct
    -0.07
    铜
    -0.07
     İz
    -0.07
    KD
    -0.07
    POSITIVE LOGITS
     Huff
    0.08
     induc
    0.08
     Jean
    0.08
     Vern
    0.08
     viscosity
    0.08
    ulsion
    0.07
     gums
    0.07
     vinyl
    0.07
     судь
    0.07
     Chic
    0.07
    Activations Density 0.004%

    No Known Activations