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. 112200
    Prev
    Next
    INDEX
    Explanations

    Arch Linux

    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
     lok
    -0.08
     maxim
    -0.08
     makat
    -0.08
     Rich
    -0.07
    million
    -0.07
    	R
    -0.07
     nå
    -0.07
     lavish
    -0.07
     republican
    -0.07
    Rich
    -0.07
    POSITIVE LOGITS
    ательная
    0.08
    anyo
    0.08
    ನಾ
    0.07
    XP
    0.07
    atorium
    0.07
    Sin
    0.07
     Affirm
    0.07
    Cath
    0.07
     Sin
    0.07
    กรรม
    0.07
    Activations Density 0.000%

    No Known Activations