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. 7-RESID-POST-AA
    6. 1724
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     koll
    -0.09
     cannon
    -0.09
    esha
    -0.08
    周期
    -0.07
     cann
    -0.07
     melee
    -0.07
    _ind
    -0.07
     )
    -0.07
     Opportun
    -0.07
     greedy
    -0.07
    POSITIVE LOGITS
    Shel
    0.09
     amate
    0.08
     Worten
    0.08
     cre
    0.08
     sauce
    0.08
    易
    0.08
    リンク
    0.08
    tda
    0.07
    ruta
    0.07
    ২৪
    0.07
    Activations Density 0.005%

    No Known Activations