© 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. 13253
    Prev
    Next
    INDEX
    Explanations

    7

    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
    sele
    -0.08
     yaw
    -0.08
    ors
    -0.07
    TB
    -0.07
    MLElement
    -0.07
    solo
    -0.07
     liquor
    -0.07
    টির
    -0.07
    ੰਗ
    -0.07
    deps
    -0.07
    POSITIVE LOGITS
     Verd
    0.08
    реж
    0.08
     వచ్చ
    0.08
     prelim
    0.08
    0.08
     welkom
    0.07
     dono
    0.07
     finest
    0.07
    皆
    0.07
     �
    0.07
    Activations Density 0.002%
    No Known Activations