© 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. 1178
    Prev
    Next
    INDEX
    Explanations

    appropriate

    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
    う
    -0.08
    megi
    -0.08
    PF
    -0.08
     hue
    -0.08
    そう
    -0.07
    strom
    -0.07
    .me
    -0.07
     FEL
    -0.07
    Keith
    -0.07
     spite
    -0.07
    POSITIVE LOGITS
     �
    0.08
    ображ
    0.08
     disclaim
    0.08
     vrem
    0.08
     dashed
    0.08
     slav
    0.08
     witty
    0.07
     ה
    0.07
     casualty
    0.07
     slurry
    0.07
    Activations Density 0.042%

    No Known Activations