© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1242
    Prev
    Next
    INDEX
    Explanations

    page

    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
     foli
    -0.08
     Mink
    -0.07
    भर
    -0.07
    .reader
    -0.07
    pieces
    -0.07
     dost
    -0.07
     viajes
    -0.07
    OLVE
    -0.07
     Estimates
    -0.07
     circum
    -0.07
    POSITIVE LOGITS
    ⭐
    0.09
     ⭐
    0.08
     जनता
    0.08
     chant
    0.07
     jai
    0.07
     disciplinary
    0.07
    티
    0.07
     helm
    0.07
     sway
    0.07
     ಆಡ
    0.07
    Activations Density 0.008%

    No Known Activations