Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 129651
    Prev
    Next
    INDEX
    Explanations

    early adopters or beta releases

    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
     уменьш
    -0.09
     квадрат
    -0.09
     olunan
    -0.08
     შეც
    -0.08
    ССР
    -0.08
    råde
    -0.08
     ydych
    -0.08
     Dicken
    -0.08
    rstrip
    -0.08
    өл
    -0.08
    POSITIVE LOGITS
     prototype
    0.11
    signup
    0.10
     MVP
    0.10
     prototypes
    0.09
    注册
    0.09
    .initial
    0.09
    .signup
    0.09
     注册
    0.09
     provisional
    0.09
    visional
    0.09
    Activations Density 0.035%

    No Known Activations