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. 43882
    Prev
    Next
    INDEX
    Explanations

    Start of texts/sentences

    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
    ుం�
    -0.09
     lijst
    -0.09
    FOUND
    -0.09
     sued
    -0.09
    OURS
    -0.09
     estat
    -0.08
     kasebut
    -0.08
    =>$
    -0.08
     depended
    -0.08
    zoals
    -0.08
    POSITIVE LOGITS
     pressing
    0.08
    ्यम
    0.08
     psychic
    0.07
     наступ
    0.07
     ситуа
    0.07
     będzie
    0.07
    ','.
    0.07
     поможет
    0.07
     therapeutic
    0.07
     dar
    0.07
    Activations Density 0.105%

    No Known Activations