© 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. 3-RESID-POST-AA
    11. 2545
    Prev
    Next
    INDEX
    Explanations

    USA

    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
    ker
    -0.08
    rasında
    -0.08
     diferencia
    -0.07
     arbet
    -0.07
     br
    -0.07
     groß
    -0.07
    Pra
    -0.07
     serp
    -0.07
    pack
    -0.07
    igsaw
    -0.07
    POSITIVE LOGITS
     вед
    0.09
     Loy
    0.08
     Clayton
    0.08
    mile
    0.07
     Teng
    0.07
     inclination
    0.07
     Libre
    0.07
    apang
    0.07
     tph
    0.07
     Sid
    0.07
    Activations Density 0.004%

    No Known Activations