© 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. 1024
    Prev
    Next
    INDEX
    Explanations

    bolded text

    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
     Kern
    -0.09
    											
    -0.08
     الأغ
    -0.08
    nya
    -0.08
    issi
    -0.08
     millennials
    -0.08
    ण्ड
    -0.08
    strlen
    -0.07
    -ה
    -0.07
    klary
    -0.07
    POSITIVE LOGITS
     செயல
    0.08
    ுடன்
    0.08
     stor
    0.07
     trades
    0.07
    豹
    0.07
    Стоимость
    0.07
    .dd
    0.07
     Portions
    0.07
     afloat
    0.07
    .SIZE
    0.07
    Activations Density 0.002%

    No Known Activations