© 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. 47563
    Prev
    Next
    INDEX
    Explanations

    imaginary

    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
     مراق
    -0.08
     THAT
    -0.08
     కల
    -0.07
     DAG
    -0.07
     wurdt
    -0.07
     Arms
    -0.07
     WT
    -0.07
     Lumi
    -0.07
    _PROC
    -0.07
    זה
    -0.07
    POSITIVE LOGITS
    .imag
    0.09
    atak
    0.08
    Imag
    0.08
     conductor
    0.08
     convertible
    0.08
     Imag
    0.08
     imaginary
    0.08
    dominal
    0.08
     impedance
    0.08
    -axis
    0.07
    Activations Density 0.006%

    No Known Activations