© 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. 19-RESID-POST-AA
    11. 103266
    Prev
    Next
    INDEX
    Explanations

    programming commands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.08
     hablando
    -0.08
     beurt
    -0.08
    -0.08
     representing
    -0.08
    -0.08
    -0.08
    ERCENT
    -0.07
    กรณ์
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    /include
    0.17
    /manage
    0.16
    /use
    0.15
    /delete
    0.15
    /write
    0.15
    /check
    0.15
    /get
    0.15
    /send
    0.15
    /search
    0.15
    /build
    0.14
    Activations Density 0.051%
    No Known Activations