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. 105985
    Prev
    Next
    INDEX
    Explanations

    Blind review

    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
     PIX
    -0.08
     EXISTS
    -0.08
     SMALL
    -0.08
     multiplying
    -0.08
     THEM
    -0.08
    וסק
    -0.08
     DIGITAL
    -0.08
    	ON
    -0.07
     REQUIRE
    -0.07
     vorhand
    -0.07
    POSITIVE LOGITS
     anonymity
    0.12
     anonym
    0.11
     anonymously
    0.11
    匿名
    0.10
     anonim
    0.10
    blind
    0.09
     anonymous
    0.09
     impartial
    0.09
     shuffled
    0.09
    编号
    0.08
    Activations Density 0.008%

    No Known Activations