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. 108995
    Prev
    Next
    INDEX
    Explanations

    angles

    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
     uses
    -0.07
     psyched
    -0.07
     zones
    -0.07
     edgy
    -0.07
     resistant
    -0.07
     detained
    -0.07
    ياجات
    -0.07
    സ
    -0.07
     immune
    -0.07
     книги
    -0.07
    POSITIVE LOGITS
     અંગ
    0.08
     ընթաց
    0.08
     त्या
    0.08
    allar
    0.08
     সেই
    0.08
     þá
    0.08
    。另外
    0.08
    assembl
    0.07
     তখন
    0.07
     આંત
    0.07
    Activations Density 0.027%

    No Known Activations