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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88112
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     cant
    -0.07
     inc
    -0.07
     tuner
    -0.07
     ><
    -0.07
    125
    -0.07
     खाली
    -0.07
    ավորապես
    -0.07
     ABOUT
    -0.07
     Jessica
    -0.07
    орно
    -0.07
    POSITIVE LOGITS
    。但
    0.10
    。当然
    0.09
    。ただ
    0.09
    。不过
    0.08
    Works
    0.08
    。」
    0.08
    。また
    0.08
    。这
    0.08
    ,以
    0.08
    。而
    0.08
    Activations Density 0.043%

    No Known Activations