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. 101626
    Prev
    Next
    INDEX
    Explanations

    math word problems

    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
    wl
    -0.09
    pleted
    -0.08
    %);↵
    -0.08
    oload
    -0.08
     *);↵
    -0.08
    ules
    -0.07
    ():↵↵
    -0.07
    ):↵↵
    -0.07
    ULE
    -0.07
    дэ
    -0.07
    POSITIVE LOGITS
     ری
    0.09
     Rey
    0.08
     unrealistic
    0.08
     unnatural
    0.08
     tempered
    0.08
     exagger
    0.08
     gigant
    0.08
    န္
    0.08
     rej
    0.08
     towers
    0.08
    Activations Density 0.223%

    No Known Activations