© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48598
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     төмен
    -0.08
    しま
    -0.07
    �
    -0.07
     İn
    -0.07
    �ન
    -0.07
    IVERY
    -0.07
    ************************************************************************
    -0.07
     Abs
    -0.07
    astype
    -0.07
    Abs
    -0.07
    POSITIVE LOGITS
    ��
    0.11
    �
    0.09
    �物
    0.09
    ڪٽ
    0.08
    ક્ટ
    0.08
     zeit
    0.08
    چا
    0.08
     hank
    0.08
    ��
    0.08
    ന്ദ്ര
    0.08
    Activations Density 0.000%

    No Known Activations