Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8558
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    门
    -0.08
     abandonment
    -0.08
     rejected
    -0.08
     Jackson
    -0.08
    ਾਇ
    -0.07
     wards
    -0.07
     abolished
    -0.07
     HUD
    -0.07
    ति
    -0.07
     door
    -0.07
    POSITIVE LOGITS
     divisible
    0.09
     factorial
    0.09
    Bez
    0.09
    Polynomial
    0.09
     nevez
    0.09
     Bez
    0.09
     نسل
    0.09
    lamiento
    0.08
    gomery
    0.08
     dugo
    0.08
    Activations Density 0.033%

    No Known Activations