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. 58904
    Prev
    Next
    INDEX
    Explanations

    all

    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
    jack
    -0.08
    Jack
    -0.08
    SHIP
    -0.08
     toxin
    -0.08
     Shirley
    -0.07
    自主
    -0.07
    ufe
    -0.07
     uc
    -0.07
    QP
    -0.07
     Jack
    -0.07
    POSITIVE LOGITS
    �
    0.08
    ๆ
    0.08
     तरह
    0.08
    وال
    0.07
     Garner
    0.07
    kte
    0.07
     Anders
    0.07
     piled
    0.07
     ๆ
    0.07
     Veget
    0.07
    Activations Density 0.013%

    No Known Activations