© 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. 65616
    Prev
    Next
    INDEX
    Explanations

    have

    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
    화
    -0.08
     Holm
    -0.08
     часу
    -0.08
     namun
    -0.08
    voli
    -0.07
    letic
    -0.07
     wrongly
    -0.07
    甚至
    -0.07
    ahal
    -0.07
     smartphone
    -0.07
    POSITIVE LOGITS
    Established
    0.09
     Established
    0.08
     established
    0.08
     দুটি
    0.08
     etabl
    0.08
     entendre
    0.08
    Animating
    0.08
     estabelecer
    0.08
    Equation
    0.08
     intento
    0.08
    Activations Density 0.036%

    No Known Activations