© 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. 44687
    Prev
    Next
    INDEX
    Explanations

    bases

    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
     outbreak
    -0.10
     شخصية
    -0.08
     વ્યક્તિ
    -0.08
    person
    -0.08
    jpg
    -0.08
    _UINT
    -0.08
    édi
    -0.08
     જાન
    -0.08
    hold
    -0.07
     PERSON
    -0.07
    POSITIVE LOGITS
     nối
    0.08
     fina
    0.08
    Sides
    0.08
     doub
    0.08
    .headers
    0.08
     sides
    0.08
     tykk
    0.08
    _headers
    0.08
     Headers
    0.08
    Scrolling
    0.08
    Activations Density 0.009%

    No Known Activations