© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26088
    Prev
    Next
    INDEX
    Explanations

    sculpt

    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
     Goethe
    -0.08
     Antwerp
    -0.08
    UNO
    -0.08
     વચ્ચે
    -0.08
     Besitz
    -0.08
     Goed
    -0.08
     alliance
    -0.08
     Schwierigkeiten
    -0.07
     possessed
    -0.07
     Ut
    -0.07
    POSITIVE LOGITS
    ض
    0.08
    XA
    0.08
     weekends
    0.08
    Recipes
    0.07
     hires
    0.07
    ienta
    0.07
    Θ
    0.07
    静
    0.07
     الض
    0.07
    -AA
    0.07
    Activations Density 0.001%

    No Known Activations