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. 12661
    Prev
    Next
    INDEX
    Explanations

    Contrasting ideas

    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
     viewpoints
    -0.08
     conséquent
    -0.08
    821
    -0.08
     daher
    -0.07
    stantial
    -0.07
     vereist
    -0.07
    DEN
    -0.07
     definitiv
    -0.07
    _SCROLL
    -0.07
    reisen
    -0.07
    POSITIVE LOGITS
    与此同时
    0.11
     gleichzeitig
    0.10
     tegelijkertijd
    0.10
     동시에
    0.10
     samtidig
    0.09
    尊
    0.09
     cave
    0.09
     preserve
    0.09
     simultaneously
    0.09
    遵
    0.09
    Activations Density 0.069%

    No Known Activations