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. 49016
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    orient
    -0.08
    ును
    -0.07
    eping
    -0.07
     resistance
    -0.07
     کیوں
    -0.07
     čist
    -0.07
    /G
    -0.07
    Pemb
    -0.07
    玩吗
    -0.07
    Arrow
    -0.07
    POSITIVE LOGITS
     importantly
    0.11
     likewise
    0.10
     Likewise
    0.09
     Tad
    0.08
     itd
    0.08
     Compart
    0.08
     {{--
    0.08
    等等
    0.08
     ஆகிய
    0.07
     usw
    0.07
    Activations Density 0.052%

    No Known Activations