© 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. 11-RESID-POST-AA
    11. 44480
    Prev
    Next
    INDEX
    Explanations

    metaphor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hin
    -0.08
     ek
    -0.08
    opin
    -0.08
    كه
    -0.07
    emens
    -0.07
     فعل
    -0.07
    FXML
    -0.07
    مش
    -0.07
     ihn
    -0.07
     Ingl
    -0.07
    POSITIVE LOGITS
    ical
    0.11
     metaphor
    0.10
     �
    0.09
     vascular
    0.08
    ery
    0.08
     بیان
    0.08
     لط
    0.07
    orical
    0.07
    /wp
    0.07
     Vita
    0.07
    Activations Density 0.011%

    No Known Activations