© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1410
    Prev
    Next
    INDEX
    Explanations

    aux

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gesproken
    -0.08
    kost
    -0.08
    played
    -0.08
    -playing
    -0.08
    _k
    -0.08
     Fact
    -0.07
     replay
    -0.07
     gespeeld
    -0.07
     كثير
    -0.07
     grapple
    -0.07
    POSITIVE LOGITS
     dentures
    0.09
     gewährleisten
    0.08
     дода
    0.08
     đảm
    0.08
     Ensure
    0.07
     নিশ্চিত
    0.07
     gewähr
    0.07
     qual
    0.07
    isso
    0.07
     bitcoins
    0.07
    Activations Density 0.000%

    No Known Activations